io.github.Vortx-AI/emem

Est-ce que io.github.Vortx-AI/emem est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.Vortx-AI/emem » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 18 outils

• emem_ask≈ 1818 tokens

  Answer a free-text question about a real-world location in one call. Signed satellite, elevation, water and built-up receipts support the answer. The tool sends the place and the question through the locate, recall and algorithm chain on the server, and returns one packaged envelope. When to use: Call this when the question is about a specific place and the answer must carry its evidence. Send the question as `q`, with `place`, `cell` or `lat`+`lng`. Over MCP a point answer is a projection. It has `answer`, `receipt` (cite `receipt.fact_cids`), `place_resolved`, `routed_to`, `facts_summary`, `algorithm_outcomes_summary`, `spatial_trace` and `scene_url`. It has `model_answer` if you sent `model`, and `_projection`, which names what the projection removed. POST /v1/ask has more: `caveats`, `topic_routing`, `reasoning`, and `inventory` with include:["inventory"]. A `routed_to` other than answer comes back complete. The answer gives a current value. For how X changed, use emem_intent did_change or emem_diff. Example arguments: {"q":"is this neighbourhood flood-prone for a flat purchase","place":"Ashok Nagar, Ranchi"}

  Paramètres, retour & exemple (11)

  Paramètres

  • q · string · requis
    User's natural-language question about the place (e.g. "is this neighbourhood flood-prone").
  • lat · number · optionnel
    WGS-84 latitude (paired with `lng`; alternative to `place` / `cell`).
  • lng · number · optionnel
    WGS-84 longitude (paired with `lat`).
  • cell · string · optionnel
    cell64 string (alternative to `place`, use when you have one from a prior emem_locate / emem_recall response). Provide this OR `place` OR `lat`+`lng`.
  • model · string · optionnel
    Optional. Compose an EXTRA prose answer with a named model, returned as `model_answer` beside the deterministic `answer`. It does not replace it: `answer` is synthesised from the structured fields and never calls a model, so every number in it traces to a fact_cid, and asking for a model must not turn a checkable answer into an unchecked one. `model_answer` carries provenance.class = model_output. Name it by base_model (`nvidia/Cosmos3-Edge`), by family (`cosmos3_edge`, `gemma`), or by any fragment naming exactly one of them (`cosmos`); a fragment matching several is refused and names them; an unroutable name is refused with the list of routable ones, and a routable model whose service is not answering is refused as busy or down rather than silently substituted. Cosmos is refused while its host has no GPU.
  • place · string · optionnel
    Free-text place name (e.g. "Mount Fuji", "Ashok Nagar, Ranchi"). REQUIRED unless `cell` or `lat`+`lng` is provided. Extract the noun phrase from the user's turn; the responder geocodes via OSM Nominatim.
  • query · string · optionnel
    Alias for `q`.
  • include · array · optionnel
    Opt-in REST envelope sections. `reasoning` drops `algorithms_for_question`; add `algorithms` to keep it. The MCP projection ignores these.
  • verbose · boolean · optionnel
    REST only: true adds per-algorithm formulas, band metadata and long prose. The MCP projection is small (about 7 KB) either way; the REST envelope is larger.
  • question · string · optionnel
    Alias for `q`.
  • include_image · boolean · optionnel
    Bundle a Sentinel-2 RGB scene URL for the resolved cell. Adds ~1-2 s on first call.

  Exemple d'appel

  {"name": "emem_ask", "arguments": {"q": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"cell": "texte", "_means": "texte", "answer": "texte", "schema": "texte", "question": "texte", "spatial_trace": {}}}

• emem_echo_verify≈ 1101 tokens

  Grade a value that you will emit against the signed fact that your citation cites. The tool returns `matches`. When the value does not match, it also returns the `drift` between your value and the value in emem. This step catches a transcription error that would otherwise be a silent wrong number. A model can resolve a fact correctly and still type `0.2411` for `0.241103`. No other step in the loop sees this. Memory algebra: the `verify` operation (https://emem.dev/docs/model.html). When to use: Call this immediately before you publish, log or pass on a value from an emem fact. Treat a false `matches` as a stop, not a warning. Use `value_verbatim` from resolve: quote that exact decimal string, then echo-verify the text you emitted. For a due-diligence or compliance record, this gives a signed check for each citation. Then you can state `every cited value was echo-verified`. The tool also accepts a bare cid, so a damaged citation still gets a grade. Example arguments: {"token":"emem:fact:defi.zb572.xoso.zb1ec:4qj3l4mgh7ch5kvxmkqspjdl6y42oqhm42khh3gostccpixkbz5q","claimed_value":"-0.0522"}

  Paramètres, retour & exemple (3)

  Paramètres

  • token · string · requis
    The citation you used. Any form resolve accepts, including a bare cid, which answers with `degraded: true`: a bare cid asserts no location, so the cell-binding check is skipped and the grade covers the value only. A cid that is not 52 characters is refused as a damaged citation rather than as a missing one, and must not be retried.
  • strict · boolean · optionnel
    Require BYTE-IDENTICAL equality. Default false, which also accepts a numerically equal value spelled differently (0.50 for 0.5). It changes exactly one outcome: the numerically-equal-but-respelled case, which passes by default and becomes `drift: "reformatted"` here. `rounded` and `wrong` already fail either way, so `strict` never turns a pass into a pass. It is also inert when `claimed_value` came in as a JSON number, because the respelling then happened in the JSON parser, before this tool saw it.
  • claimed_value · string|number · requis
    The value you are about to publish, as a string or a number. Send it as a STRING, character for character as you will emit it. A JSON number is stringified before the comparison, so `0.50` arrives as `0.5` and `0.2411000` as `0.2411` (measured against the live responder): the trailing digits this check exists to defend are gone before it runs. Quote `value_verbatim` from resolve as a string and echo the exact characters you will publish.

  Exemple d'appel

  {"name": "emem_echo_verify", "arguments": {"token": "texte", "claimed_value": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"drift": "texte", "token": "texte", "matches": true, "receipt": {}, "degraded": true, "fact_cid": "texte", "claimed_value": "texte", "canonical_token": "texte", "offline_verify_at": "texte", "resolved_value_verbatim": "texte"}}

• emem_entity≈ 834 tokens

  Give a real-world object (a bridge, a farm plot, a river, a named place) one shared identity. Every agent resolves this identity the same way. The result is an `entity_token` (`emem:entity:<entity_cid>`) and a signed receipt that shows how the reference resolved. Two agents that name the same object get the SAME entity_cid. A stable external id (Overture GERS or OSM) decides identity when the responder knows one, so different labels for one object collapse to one id. This stops referential drift: 'the damaged bridge near the river' becomes one thing that every model reasons about. When to use: Call this when a conversation refers to a THING and you need a handle that travels between agents. Anchor it with `place`, `cell` or `lat`+`lng`. Give the `emem:entity:` token to a peer, and the peer gets the same object. Recall at its cell64 to read signed facts. Choose the correct sibling: this tool MINTS or returns an identity. `emem_entity_resolve` finds an identity that an agent registered before, from a fuzzy phrase. `emem_entity_link` records that two names mean one object. Do not use it for an observation (use emem_recall or emem_memory_token) or for a place (use emem_locate). An entity is a thing AT a place. Example arguments: {"label":"Golden Gate Bridge","kind":"bridge","place":"Golden Gate Bridge, San Francisco"}

  Paramètres, retour & exemple (9)

  Paramètres

  • lat · number · optionnel
    Latitude anchoring the object to a place, paired with lng. The identity is hashed from this anchor, so two agents anchoring the same object differently mint different entities.
  • lng · number · optionnel
    Longitude, paired with lat.
  • cell · string · optionnel
    cell64 to anchor the object directly (no geocode).
  • kind · string · optionnel
    Object class: bridge, river, farm_plot, building, admin_division, place, custom, ... Defaults to "place".
  • label · string · requis
    Human name of the object, e.g. "Golden Gate Bridge", "the north dam". Required.
  • place · string · optionnel
    Free-text place to anchor the object (geocoded). Provide place OR cell OR lat+lng.
  • parent · string · optionnel
    Optional parent entity_cid (containment).
  • attester · object · optionnel
    ed25519 binding, verified. Omit it and the refusal's details.how_to_sign gives the digest to sign.
  • external_ids · object · optionnel
    Stable ids that drive convergence. Caller-supplied values win over geocoder-derived ones.

  Exemple d'appel

  {"name": "emem_entity", "arguments": {"label": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• emem_entity_link≈ 583 tokens

  Record a signed, ATTRIBUTED claim that a label or an external id (GERS, OSM, Wikidata) names an existing object. With `stance: "disputes"`, record that it does not. This is a write to the shared space: it changes what other agents resolve. The responder stores it with your key, limits the rate for each key, and weighs it by how many INDEPENDENT keys agree. Every reader sees the binding of one key as the claim of one key, never as the answer. When to use: Call this when you can confirm that two names mean one object, or to attach an authoritative external id. Your key goes on the record. Use `stance: "disputes"` when the binding of another key is wrong. The dispute goes beside it and deletes nothing. A second key on a correct single-key binding is useful by itself. Example arguments: {"entity_token":"emem:entity:0a1b2c3d4e5f60718293","alias":"the north dam"}

  Paramètres, retour & exemple (6)

  Paramètres

  • alias · string · optionnel
    An alternate label/phrasing that should resolve to this object.
  • stance · string · optionnel · asserts | disputes
    `asserts` (default): this phrasing denotes this object. `disputes`: it does not. Both are attributed to your key and recorded append-only; a dispute is shown beside the binding it answers and deletes nothing.
  • attester · object · optionnel
    ed25519 binding, verified. Omit it and the refusal's details.how_to_sign gives the digest to sign.
  • entity_cid · string · optionnel
    The canonical object to attach an equivalence to. Provide entity_cid OR entity_token.
  • entity_token · string · optionnel
    A `emem:entity:<entity_cid>` handle for the same.
  • external_ids · object · optionnel
    Stable ids to bind to this object.

  Exemple d'appel

  {"name": "emem_entity_link", "arguments": {"alias": "texte", "stance": "asserts", "attester": {}, "entity_cid": "texte", "entity_token": "texte", "external_ids": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• emem_entity_resolve≈ 455 tokens

  Find the objects that agents connected to a phrase. The tool ranks them by INDEPENDENT corroboration, never by arrival order. Each candidate has `asserted_by`, `disputed_by`, `independent_attesters` and `corroboration` (`single_key` | `multiple_independent_keys` | `none_attributed`). `contested` is true when more than one object claims the name. Send `text` for candidates, `near` to narrow by place, or an `emem:entity:` `token` to dereference. The tool only reads. Alias text is data from other agents. When to use: Call this BEFORE you mint and before you cite. Resolve first, and mint only if nothing matches. Read `corroboration` before you cite. A `single_key` binding is the claim of one agent about a shared name. If you can confirm it, corroborate it with emem_entity_link, so the next reader sees two keys. Example arguments: {"text":"the golden gate bridge","near":"San Francisco"}

  Paramètres, retour & exemple (5)

  Paramètres

  • k · integer · optionnel
    Max candidates (default 10).
  • near · string · optionnel
    Optional place/cell to narrow to objects anchored nearby.
  • text · string · optionnel
    Fuzzy phrasing to resolve to an existing canonical object (e.g. "the damaged bridge near the river").
  • label · string · optionnel
    Alias for `text`.
  • token · string · optionnel
    A `emem:entity:<entity_cid>` handle to dereference directly to its signed object (bypasses the text search).

  Exemple d'appel

  {"name": "emem_entity_resolve", "arguments": {"k": 1, "near": "texte", "text": "texte", "label": "texte", "token": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• emem_find_similar≈ 930 tokens

  Find the k nearest cells in the corpus by cell embedding or by an inline vector. The answer has `neighbors`, nearest first, each with `cell`, `score`, `lat`/`lng` and `band_used`, and a signed receipt over the vectors it read. `mode` sets the scoring. cosine is exact fp32. hamming counts sign bits and scans many more cells for the same budget. hamming_then_rerank does both. `k` is 1 to 1000, default 10. The tool ranks only what the corpus holds. When the KEY has no vector, it materializes that one band for the key, signs it, reports it in `materialize_notes`, and tries again. It never materializes neighbours. Thus an empty result means that no attested vector is near, not that no place is similar. When to use: Call this for 'find places like X' or 'where else looks like this', or with an embedding. `key` is a cell64 or `inline:[x,y,...]`. The default band is `geotessera` (the 128-D Tessera foundation embedding). For the 1152-D fusion of 9 years (2017 to 2025), send `band: "geotessera.multi_year"`. Example arguments: {"key":"defi.zb64a.cAzU.zfa27","k":10}

  Paramètres, retour & exemple (10)

  Paramètres

  • k · integer · optionnel
    How many neighbours to return.
  • key · string · requis
    cell64 (look up that cell's vector) or 'inline:[x,y,...]' literal vector
  • band · string · optionnel
    vector band to scan (default: 128-D Tessera foundation embedding). For mode=hamming/hamming_then_rerank you can pass either the cosine band (e.g. 'geotessera') or its binary sibling ('geotessera.bin128'), the responder picks the right one.
  • cell · string · optionnel
    Alias for `key`.
  • mode · string · optionnel · cosine | hamming | hamming_then_rerank
    Scoring mode. cosine = fp32 over full vector (precise, ~256 B/cell scan). hamming = sign-bit popcount over the binary sibling band (~16 B/cell, ~1000× faster, ~65% recall@10). hamming_then_rerank = triage with Hamming on 4·k candidates then re-rank by cosine, matches cosine precision at ~16× less work.
  • scope · object · optionnel
    Multi-tenant scope `{user_id, agent_id, run_id, org_id}`. Setting it bypasses the ANN index entirely, because that index carries no scope column, and runs the brute-force scan instead: the tenant filter is honoured truthfully, and the call is slower.
  • cell64 · string · optionnel
    Alias for `key`.
  • filter · object · optionnel
    Claim-algebra predicate evaluated against every candidate before ranking. A cell with no fact for the filter's band is DROPPED rather than treated as false, so 'places like X where NDVI > 0.5' never silently includes cells with no NDVI.
  • as_of_tslot · integer · optionnel
    Bi-temporal valid-time bound. Applied to candidate cells BEFORE cosine scoring, a cell with no fact whose tslot ≤ as_of_tslot under the scoring band is dropped from the candidate pool (undecidable→drop). When set, the Lance ANN fast-path is bypassed (the index has no signed_at column); brute-force k-NN runs instead so as_of is honoured truthfully.
  • as_of_signed_at · string · optionnel
    Bi-temporal transaction-time bound (RFC 3339). Also applied to candidates BEFORE cosine. Same Lance-bypass note as as_of_tslot.

  Exemple d'appel

  {"name": "emem_find_similar", "arguments": {"key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• emem_guard_verdict≈ 1532 tokens

  Run the emem-guard policy checks on text before you send it. The checks use this responder's corpus. The tool finds every emem: citation, resolves each one, and returns allow or deny with a reason that a machine can read: `EMEM-GUARD DENY <CODE> token=<token|-> fix=<fix> leaf=<leaf|->`. The codes are: PROV_SIG (the signature did not verify). PROV_BYTES (the citation resolved to different content). PROV_DRIFT (the reading moved past its band threshold). PROV_VALUE (a stated value does not agree with the cited fact). CLAIM_UNGROUNDED (a measurable claim has no citation; turn it on with claim_gating). `fix` tells you what to do: refresh_token, remove_reference, contact_admin, cite_observation, correct_value. Only a self-hosted guard returns GEO_ZONE and redact_and_retry. This tool is ADVISORY: it blocks nothing. A citation that this responder does not hold is never a denial, because it can be a citation from another responder. Memory algebra: the `verify` operation (https://emem.dev/docs/model.html). When to use: Call it on your draft before you assert something, or on a tool result before you reason on it. Then you can fix a citation that does not resolve. With `claim_gating: true`, it also names measurable claims with no citation, and the band that answers each. For a payload from another framework (CloudEvent, OPA input, OpenAI moderations body, a tool call from another server), send it unchanged and name its `shape`. The default reader reads only `texts`, and a check that read nothing answers allow. To ENFORCE the policy, use emem_guard_selfhost. It returns the procedure for your own node. Example arguments: {"texts":["Lusail ground sits at 2.6 m per emem:fact:defi.zb521.jawI.gOze:f3yr3urkrfwamlemwadulgth2qpw645vi6l6fhtuu4dy5o7onahq"]}

  Paramètres, retour & exemple (4)

  Paramètres

  • agent · string · optionnel
    Optional free-text label for who is asking. Advisory only, never a trust boundary.
  • shape · string · optionnel · native | mcp | openai | cloudevent | policy
    Which envelope YOUR payload is in, so you never have to reshape it to ask the question: send the body your own framework produced and name its shape. native reads `texts`; `mcp` reads a JSON-RPC tools/call or tool result; `openai` reads a moderations (`input`) or chat-completions body; `cloudevent` reads a CloudEvents 1.0 structured event; `policy` reads {input}. It matters: a CloudEvent whose citation sits at data.text is invisible to the native reader, and a check that read nothing answers `allow`, so confirm `citations_found` matches what you sent. Unrecognised values fall back to native rather than erroring. This selects how the body is READ only — the verdict always comes back in this tool's declared output shape, because a tool that declares an outputSchema owes conforming structuredContent. To get the ANSWER translated into the same envelope too (an OPA `result:{allow,deny}`, an MCP CallToolResult to substitute on a deny), call POST /v1/guard/verdict?shape=… directly.
  • texts · array · optionnel
    Free text to check, and the only input this tool needs. Send just the pieces the question is about: a draft answer, a tool result, one turn. Do not send surrounding conversation, because nothing here reads it and a checker should ask for the smallest input that answers the question.
  • claim_gating · boolean · optionnel
    Also flag measurable physical-world claims that carry NO citation (deny code CLAIM_UNGROUNDED, fix cite_observation). Off by default: it reports on the absence of a citation rather than on a failed check. The verdict names the sentence, the magnitude, and the emem band that would answer it.

  Exemple d'appel

  {"name": "emem_guard_verdict", "arguments": {"agent": "texte", "shape": "native", "texts": [], "claim_gating": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"fix": "refresh_token", "code": "PROV_SIG", "claim": {}, "action": "allow", "checked": 1, "receipt": {}, "advisory": true, "citations": [], "citations_found": 1, "citations_verified_here": 1}}

• emem_intent≈ 1856 tokens

  State what you want in one typed object and get the answer. You do not choose a primitive. `type` selects the intent AND the other fields that the tool reads. Send only the fields in its row. The plan runs in the same call: you get results, not a list of calls. type | needs | optional | answers where_is | description | | cell64 for a named place what_is_here | cell OR place | description | what is attested at a location is_like | a, b | | cosine similarity of two cells did_change | cell, band, window | | delta for one band over [start,end] tslots find_like | key | k, filter | nearest cells by embedding confirm | claim, cell | | verdict and the signed facts behind it ask | description | place/cell/lat+lng | free-text question, packaged answer area_over_time | geometry, bbox OR areas; start_date, end_date | index, max_scenes | index of an area for each overpass, with spread and anomaly An unknown or missing `type` returns a `needs_intent_type` envelope with the valid values. It is not a hard error. When to use: Call this when the question matches one of the eight rows and you prefer to state the goal. Otherwise call the primitive. A band at a cell is emem_recall. A region is emem_recall_polygon. A free-text question about a place is emem_ask (type:"ask" sends it there). `window` takes tslots, not dates: get them from emem_trajectory. `areas` puts up to 6 areas on one chart. You can call a tool that this text names but your list does not show, by name, through tools/call. Example arguments: {"type":"did_change","cell":"defi.zb64a.cAzU.zfa27","band":"indices.ndvi","window":[20245,20620]}

  Paramètres, retour & exemple (21)

  Paramètres

  • a · string · optionnel
    is_like only: cell64 of the first place in the pair.
  • b · string · optionnel
    is_like only: cell64 of the second place. The answer is a cosine similarity in [-1,1] over the two cells' embeddings.
  • k · integer · optionnel
    find_like only: how many neighbours to return.
  • key · string · optionnel
    find_like only: cell64 to search from, ranked by embedding cosine.
  • lat · number · optionnel
    ask only: latitude, paired with `lng`, when you want to pin the location by coordinate rather than by name or cell64.
  • lng · number · optionnel
    ask only: longitude, paired with `lat`.
  • band · string · optionnel
    did_change only: which band to test, e.g. "indices.ndvi". One band per call; the answer is a delta over `window`, not a whole-cell diff.
  • bbox · object · optionnel
  • cell · string · optionnel
    cell64 address, e.g. "defi.zb64a.cAzU.zfa27". Required by did_change and confirm. Optional for what_is_here and ask: supply it to skip geocoding, omit it and give `place` instead.
  • type · string · requis · where_is | what_is_here | is_like | did_change | find_like | confirm | ask | area_over_time
    Which intent; the table in the description gives each row's fields.
  • areas · array · optionnel
    area_over_time: up to 6 {id,geometry|bbox} on one chart
  • claim · object · optionnel
    confirm only: the claim to test at `cell`, e.g. {"band":"indices.ndvi","op":"gt","value":0.4}. The answer is a verdict plus the signed facts it rests on.
  • index · string · optionnel · ndvi | ndwi | ndmi | lswi | evi | vv | vh | vh_vv
  • place · string · optionnel
    Free-text place name for what_is_here and ask when you have a name but no cell64, e.g. "Ashok Nagar, Ranchi". The responder geocodes it. Ignored when `cell` is present.
  • filter · object · optionnel
    find_like only: optional claim constraining which cells may be returned. Same object as `claim` below, same ops, same required fields.
  • window · array · optionnel
    did_change only: exactly two tslots, [start, end], band-tempo-relative integers from the emem epoch (NOT unix seconds or a date string). Get valid tslots for a cell from emem_trajectory.
  • end_date · string · optionnel
    YYYY-MM-DD
  • geometry · object · optionnel
    area_over_time: GeoJSON Polygon; or bbox {min_lat,min_lng,max_lat,max_lng}.
  • max_scenes · integer · optionnel
  • start_date · string · optionnel
    YYYY-MM-DD
  • description · string · optionnel
    where_is: the place to resolve, e.g. "Mount Everest". ask: the user's question, forwarded verbatim. what_is_here: optional free text used as the question and, if `place` is absent, as the place. Ignored by the other intents.

  Exemple d'appel

  {"name": "emem_intent", "arguments": {"type": "where_is"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• emem_locate≈ 646 tokens

  Get the canonical address (cell64) of a real-world place. Every agent resolves a place to the same cell64, so two models refer to the same ground. The answer also lists, by topic, the bands and algorithms that you can recall there. For an OBJECT identity (a bridge, a plot) instead of a cell, use emem_entity. Send `lat`+`lng` as numbers, or a free-text place. When both arrive, the coordinates win. `q`, `query` and `name` are other names for `place`. The answer lists keys that this schema does not declare in `_unrecognised_arguments`, so a typo is visible. When to use: Call this when the next step needs the cell64 of a named place, or the bands that exist there. `data_at_this_cell` lists every band you can recall, by topic (`live_bands_by_topic`), the recipes that use them (`algorithms_for_topic`), and the bands with no materializer here. For one packaged answer in one call, use `emem_ask`. Example arguments: {"place":"Mount Everest"}

  Paramètres, retour & exemple (6)

  Paramètres

  • q · string · optionnel
    Alias for `place`, accepted because OSM/Mapbox/Google Geocoding all use `q`. Provide either this or `place` (or `lat`+`lng`).
  • lat · number · optionnel
    WGS-84 latitude in degrees, paired with `lng`. REQUIRED with `lng` unless `place`/`q` is provided.
  • lng · number · optionnel
    WGS-84 longitude in degrees, paired with `lat`. REQUIRED with `lat` unless `place`/`q` is provided.
  • name · string · optionnel
    Alias for `place`.
  • place · string · optionnel
    Free-text place name (e.g. 'Mount Everest', 'Tokyo'). REQUIRED unless `lat`+`lng` is provided. Aliases also accepted: `q`, `query`, `name`.
  • query · string · optionnel
    Alias for `place`.

  Exemple d'appel

  {"name": "emem_locate", "arguments": {"q": "texte", "lat": 1, "lng": 1, "name": "texte", "place": "texte", "query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"next": [], "cell64": "texte", "status": "texte", "selected": {}, "place_label": "texte", "data_at_this_cell": {}}}

• emem_memory_bundle≈ 756 tokens

  Combine N (cell, band, tslot?) triples into ONE signed envelope. Each triple goes through the standard recall path, which materializes on a miss. The tool puts the resulting fact_cids in a content-addressed envelope, and the responder signs the full receipt. The `bundle_token` is `emem:bundle:<bundle_cid>`: one string that cites the full set. Memory algebra: the `merge` operation (https://emem.dev/docs/model.html). When to use: Call this when you must cite several (place, band, date) facts as one handle. You can verify the bundle offline with /v1/verify_receipt. The receipt covers all the cited fact_cids and cells. Use this instead of N calls to `emem_memory_token` when the citation is one thing. An example is "the EUDR baseline for these 8 plots at 2020-12-31". The limit is 256 triples for each call. The answer gives `members` and `resolved`, so you can see a bundle that resolved only in part. Example arguments: {"triples":[{"cell":"defi.zb4d9.pefa.zf619","band":"copdem30m.elevation_mean"},{"cell":"defi.zb493.xoso.zcb6a","band":"indices.ndvi"}],"purpose":"audit baseline 2026"}

  Paramètres, retour & exemple (4)

  Paramètres

  • scope · object · optionnel
    Multi-tenant scope `{user_id, agent_id, run_id, org_id}`, applied to EVERY triple's underlying recall so the whole bundle cites only facts written under that four-tuple.
  • purpose · string · optionnel
    Optional human-readable purpose string. Included in the bundle_cid preimage so the same triples + different purposes produce distinct CIDs.
  • triples · array · optionnel
    One to 256 (cell, band, tslot?) triples to bundle. Each entry is recalled through the standard auto-materialize path; the bundle envelope cites every resulting fact_cid. 257 or more is a typed 400: the token is O(1) in size for any N, but covering N facts costs ceil(N/256) calls, so plan round trips rather than meeting the cap mid-run.
  • fact_cids · array · optionnel
    Instead of triples: the exact facts to bind, by cid. A triple is resolved through recall and can bind a newer fact than the one you showed; a cid binds that fact and no other. Pass triples or fact_cids, not both.

  Exemple d'appel

  {"name": "emem_memory_bundle", "arguments": {"scope": {}, "purpose": "texte", "triples": [], "fact_cids": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• emem_memory_contradictions≈ 933 tokens

  Find where the corpus DISAGREES with itself (algebra: competing evidence). Two or more independent sources can sign different values for the same place, band and time. This tool returns that disagreement with a severity from 0 to 1 and a citation for each disputed fact. It does not pick one value and hide the conflict. It tells you when not to trust a single answer. Read the SCOPE before you quote a zero. By default the tool counts only disagreement between two DIFFERENT attesters. One responder that answers from two upstreams counts only with `include_same_attester_sources: true`. When to use: Call this before you rely on a number: 'do the sources agree on X', 'audit this claim'. Use `cell_prefix` for a region and `band` for one band family. `min_severity` removes small differences. Severity depends on the band kind: for a scalar, the spread over the band's range. For a vector, 1 minus the mean cosine. For a category, 1 minus the share of the mode. On a single-responder node, add `include_same_attester_sources: true`. There, the most likely disagreement is one signer that answers from two providers. Each record names its `disagreement_scope`. The receipt cites every disputed cid. To measure a pair, use `emem_diff`. To read the `disagrees_with` edge, use `emem_edges_recall`. Example arguments: {"cell_prefix":"damO","band":"indices.ndvi","min_severity":0.2}

  Paramètres, retour & exemple (8)

  Paramètres

  • band · string · optionnel
    Band key filter (e.g. `indices.ndvi`). Omit to include all bands.
  • cell · string · optionnel
    Alias for `cell_prefix`, and the spelling the rest of the surface uses for a cell64. Send a cell64 you already hold and the scan narrows to that place instead of running over the corpus.
  • limit · integer · optionnel
    Max contradictions to return.
  • cell64 · string · optionnel
    Alias for `cell_prefix`.
  • cell_prefix · string · optionnel
    A cell64 to scan, or a bytewise prefix of one (e.g. `defi.zb5f9`). Omit to scan the whole corpus up to the scan cap. A full cell64 is a prefix of itself, so passing one narrows the scan to exactly that place.
  • min_severity · number · optionnel
    Severity floor in [0, 1]. 0 = report every disagreement, 1 = only flagrant. Severity scoring is per band kind: scalar (max-min over band range), vector (1 - mean cosine), categorical (1 - mode share).
  • window_unix_s · array · optionnel
    [lo, hi] inclusive Unix-seconds filter on attestations' signed_at, all disagreeing attestations must fall in the window.
  • include_same_attester_sources · boolean · optionnel
    Also report keys where ONE attester answered the same address from two different upstreams. Default false, which scans only for disagreement between two or more DISTINCT attesters — so on a single-responder corpus a zero here means the narrower question was answered, not that nothing disagrees. Set true and a key qualifies when the facts differ in `derivation.fn_key` or in their `sources[].scheme` set; the same provider re-signed is a refresh, not a disagreement, and stays excluded. Each record carries `disagreement_scope` and a `providers[]` list naming what changed.

  Exemple d'appel

  {"name": "emem_memory_contradictions", "arguments": {"band": "texte", "cell": "texte", "limit": 1, "cell64": "texte", "cell_prefix": "texte", "min_severity": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• emem_memory_token≈ 794 tokens

  Make a citation handle, `emem:fact:<cell64>:<fact_cid>` (or `:<state_cid>`). Any agent or LLM resolves it to the same signed object, byte for byte. Give this one string to another agent instead of a new description of the fact. The tool checks that both parts are not empty and do not contain the `:` separator. Memory algebra: the `cite` operation (https://emem.dev/docs/model.html). When to use: Call this when you need one string that cites a place and an attested fact across messages, agents or tools. Use `emem_echo_verify` before you publish the value. FOR MANY FACTS, USE emem_memory_bundle. This is a measured result. A token is 83 to 84 characters and 51 LLM tokens. The value it cites is 11 characters and 5.4 tokens on average. Thus N tokens use about 9.5 times the context of the N numbers. A bundle is 38 characters for any N up to 256, and it resolves in one round trip. It costs less than tokens from N=1, and less than the plain values from N=5. Use one token to cite ONE fact that you must verify later. Example arguments: {"cell":"defi.zb493.xoso.zcb6a","fact_cid":"cxjiu7l54ujzrpnekp24n4534yojpue4mprddbvevnqtti3lh5bq"}

  Paramètres, retour & exemple (4)

  Paramètres

  • band · string · optionnel
    Optional band key. When set, the minted citation carries the band's tamper-provenance block (class, deterministic, tamper_evidence, trust_rank) so the receiving agent sees the trust class without a resolve round-trip.
  • cell · string · requis
    cell64, neither component may contain `:`.
  • fact_cid · string · requis
    52-char base32-nopad-lowercase content-id of the fact (full 32-byte blake3).
  • observed_on · string · optionnel
    The fact's source capture date (YYYY-MM-DD) as `/v1/recall` reports it in `sources[].captured_at`. Supplied together with `band` it additionally mints the self-describing `descriptor_token`. A wrong date forges nothing: resolve binds the date to the signed fact and answers 409 on a mismatch.

  Exemple d'appel

  {"name": "emem_memory_token", "arguments": {"cell": "texte", "fact_cid": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"cell": "texte", "docs": "texte", "grammar": "texte", "fact_cid": "texte", "cell_token": "texte", "memory_token": "texte"}}

• emem_memory_token_resolve≈ 479 tokens

  Read a `emem:fact:<cell64>:<fact_cid>` citation handle and return the reading that it cites. `value`, `unit`, `band` and `kind` are at the TOP level of the answer, beside the full signed `fact` body. You do not split the token or call `GET /v1/facts/<cid>` yourself. Memory algebra: the `resolve` operation (https://emem.dev/docs/model.html). When to use: Call this when you have a memory_token from another agent or an earlier turn and need the value. For a scalar, quote `value_verbatim`, the exact decimal string that the responder signed. A null `value` or `unit` means the fact has none (an absence, or an index with no unit). It does not mean a missing field. A cid that this responder does not hold returns a typed 404. Then try /v1/fetch, or resolve at a mirror. Example arguments: {"token":"emem:fact:defi.zb493.xoso.zcb6a:cxjiu7l54ujzrpnekp24n4534yojpue4mprddbvevnqtti3lh5bq"}

  Paramètres, retour & exemple (1)

  Paramètres

  • token · string · requis
    A `emem:fact:<cell64>:<fact_cid>` citation handle to dereference.

  Exemple d'appel

  {"name": "emem_memory_token_resolve", "arguments": {"token": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"band": "texte", "cell": "texte", "kind": "texte", "unit": "texte", "value": 1, "receipt": {}, "fact_cid": "texte", "fact_url": "texte", "value_verbatim": "texte", "canonical_token": "texte"}}

• emem_recall≈ 1796 tokens

  Read the signed facts at a canonical address (cell64). When a band has no fact yet but has a registered materializer, the responder fetches it. A fact_cid names one signed attestation, so you can cite a fact and verify it again. Resolve the cid anywhere and you get the same bytes. A fact_cid is NOT a fingerprint of the observation. The digest includes the responder's key and the time it signed. Thus two responders that measure the same thing make different fact_cids, and a cid resolves only at the responder that signed it. For identity across responders, use emem_entity. Send `deterministic:true` (or a `provenance` class list) to keep only facts that you can compute from the cited raw source. In the memory algebra this is ensure(cell, bands), not get: you state what must exist. When to use: Call this after `emem_locate`, or with a cell64 or a place name. It returns every Primary fact at that (cell, band, tslot). A band can have no fact but have a materializer. Then the responder fetches the upstream value, signs it, stores it and returns it in the same call. The first call is slow; later calls use the cache. Thus any wired band recalls at any cell on Earth: send `bands: [<band>]`. `materialize_notes` lists what the call fetched. Empty notes mean no materializer here. Example arguments: {"cell":"defi.zb64a.cAzU.zfa27","bands":["weather.temperature_2m","copdem30m.elevation_mean"]}

  Paramètres, retour & exemple (14)

  Paramètres

  • lat · number · optionnel
    Explicit latitude, an alternative to `cell`; paired with `lng`.
  • lng · number · optionnel
    Explicit longitude, paired with `lat`.
  • band · string · optionnel
    optional single band key, convenience alias for bands:[band]. Use when you want exactly one band (e.g. 'geotessera.2020', 'modis.ndvi_mean') and would otherwise have to wrap it in an array. Both `band` and `bands` are accepted; if both are given they are merged.
  • cell · string · requis
    cell64 string, e.g. 'defi.zb64a.cAzU.zfa27'
  • bands · array · optionnel
    optional band keys to filter, e.g. ['indices.ndvi','geotessera']
  • place · string · optionnel
    Free-text place name, an alternative to `cell`.
  • scope · object · optionnel
    Optional multi-tenant scope {user_id, agent_id, run_id, org_id}. When at least one field is set, the recall is FILTERED to facts written under the same four-tuple (a recall scoped to {user_id:'u1'} sees only u1's facts, never another tenant's and never globally-written facts) AND the signed receipt binds the scope. Omit (or send {}) for the global, pre-v0.0.8 recall.
  • tslot · integer · optionnel
    optional time slot (band-tempo-relative integer offset from emem epoch)
  • cell64 · string · optionnel
    Alias for `cell`.
  • include · array · optionnel
    Opt-in response expansion. include:['provenance'] attaches each fact's tamper-provenance class, which is what `deterministic` and the `provenance` filter select ON: without it you can filter by class and never be told which class a returned fact is. include:['freshness'] attaches an advisory per-fact freshness block: a Q(Δt) staleness score from the band's physics decay kernel (the same one /v1/temporal_route ranks bands with), so an agent learns how stale each reading is in the call that returns it. Advisory only; it does NOT enter the receipt. include:['edges'] attaches each fact's typed temporal edges and threads their CIDs into the receipt. Absent leaves the response byte-identical to the pre-v0.0.9 recall.
  • provenance · array · optionnel
    Tamper-provenance filter: return only facts whose band's provenance class is in this list. `attested_execution` is a device reading trusted through its verified OS execution trace and platform attestation (not recomputable). Applied BEFORE the receipt is signed, so the receipt covers exactly the returned facts; `bands_already_attested_at_cell` stays unfiltered so you still see what else exists at the cell.
  • as_of_tslot · integer · optionnel
    Bi-temporal valid-time bound. Returns the latest fact per (cell,band) whose tslot ≤ as_of_tslot, answers `what did this place look like AS OF date X`. Conflicts with an explicit `tslot` when as_of_tslot < tslot (rejected with code:`invalid_temporal_bound`).
  • deterministic · boolean · optionnel
    Sugar over `provenance`: true keeps only facts any third party can recompute from the cited raw source (direct_sensor + deterministic_index); false keeps the rest (attested_execution + model_output + human_curated + unclassified). Composable with `provenance` (intersection).
  • as_of_signed_at · string · optionnel
    Bi-temporal transaction-time bound. RFC 3339 string. Returns only facts whose `signed_at` ≤ as_of_signed_at, answers `what did emem KNOW as of system-date Y`. Malformed strings are rejected with code:`invalid_signed_at_format`.

  Exemple d'appel

  {"name": "emem_recall", "arguments": {"cell": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"facts": [], "receipt": {}, "fact_order": "texte", "current_by_band": {}, "materialize_notes": [], "bands_already_attested_at_cell": []}}

• emem_tools≈ 984 tokens

  The map of emem's tools, and the one tool that finds all the others. It gives the working loop in order (name, ground, cite, resolve, verify, check for drift). Then it groups every other tool by the question it answers, each with a one-line trigger. Send `name` for the full schema of one tool and an example that runs. IF YOU SEE A LIST OF 18 TOOLS, IT IS A CURATED SUBSET OF 115, NOT THE FULL SURFACE. Hosts remove `_meta`, so this text repeats the count. You can call every catalogued tool by name through tools/call at either endpoint. When to use: Call this FIRST when you do not know which tool answers the question. Also call it when your list does not have a capability. A tool that is not in your list can still be on the server. `q` searches by topic (`ndvi`, `flood`, `verify`). `name` returns one exact schema. With no arguments, you get the full map. /mcp/full registers the full catalog. emem_ask answers in one call without a choice of primitive. Example arguments: {"q":"ndvi"}

  Paramètres, retour & exemple (6)

  Paramètres

  • q · string · optionnel
    Free-text filter over tool names, titles and trigger text, e.g. `ndvi`, `cloud`, `flood`, `verify`, `token`. Plain lowercased substring over name + title + description + trigger text, not fuzzy and not stemmed: `ndvi` hits, `vegetation index` only hits tools that spell that phrase. Combines with `shape`/`bundle`/`category`/`tier` as AND, so an over-narrow combination answers with an empty catalog rather than an error.
  • name · string · optionnel
    Return the full descriptor for exactly this tool (input schema, runnable example, annotations), e.g. `emem_ndvi`. Use this when you already know the name and want its schema without loading the whole catalog. It SHORT-CIRCUITS: when `name` is set every other argument here is ignored, so `{name, q}` is not a search within one tool. A name this responder does not carry is not an error status, you get a body with `did_you_mean` holding up to five names that share a substring with what you asked for.
  • tier · string · optionnel · core | extended | all
    Which slice to list. Defaults to `all`, so this tool shows the whole surface even when the endpoint advertises only the core loop, and an `extended` tool you find here is callable by name through tools/call whether or not your host listed it. Pass `core` to see only what a default connection advertises.
  • shape · string · optionnel · scalar | timeseries | raster | geometry | vector | identity | token | proof
    Filter by what the answer looks like, which is usually the real question. `scalar` is one number at one address; `raster` is a gridded field over an area; `timeseries` is a value per timestep; `vector` is a learned embedding; `identity` is a canonical name for a thing; `token` is a citation handle; `proof` checks one.
  • bundle · string · optionnel · tokenisation | verification | agent_to_agent | long_horizon | robotics | satellites | agriculture | forestry
    Filter by the job you are doing. Call with no arguments first to see each bundle and its size.
  • category · string · optionnel · read | write | verify | introspect | plan
    Filter to one category. This is about the shape of the job, NOT about safety: 43 tools outside `write` declare `readOnlyHint: false` because reading a cold address can materialise or mint as a side effect, so `category: "read"` is not a safe-tools filter. Read each result's `annotations.readOnlyHint` for that.

  Exemple d'appel

  {"name": "emem_tools", "arguments": {"q": "texte", "name": "texte", "tier": "core", "shape": "scalar", "bundle": "tokenisation", "category": "read"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• emem_verify_receipt≈ 831 tokens

  Verify a signed receipt on the server. The tool builds the canonical preimage again, under the rule that the receipt's `preimage_version` names. It checks the ed25519 signature with the embedded key. It returns `{valid, reason, failure_detail, signature_valid, merkle_proof_valid, signer_pubkey_b32, preimage_blake3_hex}`. A receipt verifies BYTE FOR BYTE OR NOT AT ALL. Version 2 binds the inclusion proof, so a change of any kind makes the signature fail: a dropped field, a renamed field, a summary. Use this tool when the browser page /verify is not available. Also use it to audit a receipt from a third party. When to use: Send the receipt EXACTLY as the read tool returned it, complete and unchanged. Two omissions cause a false forgery, not a 400. Do not drop `merkle_proof`. Do not drop `preimage_version`. Without it the value is 0, which selects the v0 rule, and the signature reads as invalid. The signature and the key can be byte arrays, or `sig_b32` and `responder_pubkey_b32`. The tool accepts no other names. When a field changed after signing, the answer is `reason: receipt_reshaped_after_signing` and names the field. To require a specific signer, set `pubkey_b32`. A bad signature returns 200 with `valid: false`, never a 4xx. The example (from emem_tools) is a real receipt over two Trafalgar Square facts. Unchanged, it is `valid`. Change one byte, and it is not. Example arguments: 1602 bytes, too long to inline in a listing. Call `emem_tools` with `{"name": "emem_verify_receipt"}` for it whole and runnable; it is not shortened here because a truncated example is not one.

  Paramètres, retour & exemple (4)

  Paramètres

  • facts · array · optionnel
    The fact value(s) you intend to rely on. Each is content-addressed and checked for membership in the receipt's `fact_cids`, so a genuine receipt presented beside a tampered fact answers `valid:false` / `fact_mismatch`. Omit it and only the signature is checked, which a doctored fact survives.
  • receipt · object · requis
    The signed receipt envelope, the object under `receipt` in any read primitive's result. Must carry primitive/served_at/request_id/cells/fact_cids and either `signature` byte[] + `responder_pubkey` byte[] or their b32 string forms. IF ALL YOU HOLD IS AN `emem:fact:` TOKEN, this is not the tool to call first: a token is not a receipt and passing one here is a shape error. Call `emem_memory_token_resolve` on the token, then pass THAT result's `receipt` object here. Resolving proves the token points at the bytes it claims; verifying proves this responder signed them.
  • pubkey_b32 · string · optionnel
    Optional explicit responder pubkey (base32). When omitted, uses the receipt's embedded pubkey/responder fields.
  • current_responder_epoch · integer · optionnel
    The responder key epoch you currently trust, from `/v1/manifests`. Produces an advisory `key_epoch_advisory` comparison against the receipt's epoch; a mismatch is reported, never rejected.

  Exemple d'appel

  {"name": "emem_verify_receipt", "arguments": {"receipt": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• fetch≈ 538 tokens

  Dereference an id from `search`. You get the reading in one line, then the signed body, the URL that serves those bytes, and metadata: cell, band, signing time and key. The id can be an `emem:fact:` citation, a bare fact_cid, or an `emem:cell:` handle for a full cell. The value is the exact decimal string that the responder signed, never a new format. A fact handle writes nothing. A cell handle, like `emem_recall`, MATERIALIZES a missing band on a cold cell: it fetches, signs and stores it. The flags follow that path: readOnlyHint false. When to use: Call this on each result that you will cite, before you quote the number. Quote the one-line reading. The body lets a reader check it, and emem_echo_verify grades what you emit against it. When a body is too large, the answer says so and gives the URL that serves it complete. Example arguments: {"id":"emem:fact:defi.zb493.xoso.zcb6a:cxjiu7l54ujzrpnekp24n4534yojpue4mprddbvevnqtti3lh5bq"}

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    An id from `search`: an `emem:fact:` citation, a bare fact_cid, or an `emem:cell:` handle for every fact at one cell.

  Exemple d'appel

  {"name": "fetch", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "url": "texte", "text": "texte", "title": "texte", "metadata": {}}}

• search≈ 530 tokens

  Search emem's signed corpus and get results as citations. Each entry is one signed fact. It has an `id` to dereference, a `title` with band, place and signed value, and a stable `url` that serves those bytes. The query can be a place or a question about one. ('NDVI near Mount Fuji': a topic word narrows the results and never removes all of them.) It can also be a cell64, an `emem:cell:` handle, or an emem citation, which returns the one fact it cites. The list has a cap for the wire. The first entry (index 0) names the cell and the TRUE total. On a cold cell, the tool MATERIALIZES a missing band first, as `emem_recall` does: it fetches, signs and stores it. Thus readOnlyHint false. When to use: Call this first when a question is about a place and the answer must have citations. It changes the question into a list of sources, and `fetch` expands each source. For one combined answer in one call, use emem_ask. Example arguments: {"query":"Trafalgar Square, London"}

  Paramètres, retour & exemple (1)

  Paramètres

  • query · string · requis
    A place, a question about one, a cell64 or emem:cell: handle, or an emem:fact: citation.

  Exemple d'appel

  {"name": "search", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"results": []}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://emem.dev/mcp