com.openpublica/civic-meetings

Est-ce que com.openpublica/civic-meetings est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.openpublica/civic-meetings » 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 16 outils

• discover_meeting_vocabulary≈ 465 tokens

  Discover the valid category and topic filter values before filtering a search. Meeting `category_tag`s are opaque UUIDs and topics have no fixed list, so you cannot guess them. Call this first to get the real values, then pass a returned `category_tag` (from `categories[].tags`) or `topic` string into `search_meetings_semantic` / `list_recent_meetings`. Scope with a government and/or date range; calls without explicit dates default to a recent window (returned as `default_window_days`).

  Paramètres, retour & exemple (5)

  Paramètres

  • end_date · ? · optionnel
    Optional latest date, MM-DD-YYYY.
  • start_date · ? · optionnel
    Optional earliest date, MM-DD-YYYY.
  • topic_limit · integer · optionnel
    Max topics to return, most common first (1-200).
  • government_id · ? · optionnel
    Optional account_id to scope the vocabulary to one government.
  • government_ids · ? · optionnel
    Optional list of account_ids to scope to several governments. Overrides government_id.

  Exemple d'appel

  {"name": "discover_meeting_vocabulary", "arguments": {"end_date": "texte", "start_date": "texte", "topic_limit": 1, "government_id": "texte", "government_ids": "texte"}}

  Exemple de retour

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

• find_governments_by_name≈ 276 tokens

  Resolve a place *name* to the governments OpenPublica tracks there. Use this when you know a city/state name but not its coordinates — it returns matching governments with their `account_id` (prefix matches first), which you then pass to the search/list tools. Prefer this over `find_local_governments` when starting from a name rather than a latitude/longitude.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Max governments to return (1-50).
  • query · string · requis
    A place name to search for, e.g. 'Sacramento', 'San Francisco, CA', or a state like 'Texas'.

  Exemple d'appel

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

  Exemple de retour

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

• find_governments_by_zip≈ 243 tokens

  Resolve a ZIP code to nearby tracked governments. Convenience wrapper: geocodes the ZIP, then finds the governments OpenPublica tracks nearest that point. Returns their `account_id`s plus the resolved location. An empty `governments` list means none are tracked near that ZIP yet.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Max governments to return (1-50).
  • postal_code · string · requis
    A US ZIP code, e.g. '95814'.

  Exemple d'appel

  {"name": "find_governments_by_zip", "arguments": {"postal_code": "texte"}}

  Exemple de retour

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

• find_local_governments≈ 302 tokens

  Discover which governments OpenPublica tracks near a coordinate. Returns nearby governments with their `account_id`, which you can pass to the other tools to scope results to a specific city or board. Note OpenPublica only covers a limited set of US localities; an empty result means none are tracked near that point yet.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Max governments to return (1-50).
  • latitude · number · requis
    Latitude of the location of interest.
  • longitude · number · requis
    Longitude of the location of interest.

  Exemple d'appel

  {"name": "find_local_governments", "arguments": {"latitude": 1, "longitude": 1}}

  Exemple de retour

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

• get_coverage_overview≈ 148 tokens

  Get estimated stored-record totals, not publication-filtered coverage. Counts do not establish completeness, searchability or freshness. DC is reported separately from states as `includes_dc`.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_coverage_overview", "arguments": {}}

  Exemple de retour

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

• get_document≈ 190 tokens

  One document's metadata. Use read_document_pages to read it. If an `availability` key is present, read it before quoting figures: its `problems` are transcription-lint findings, most often a footnote marker that may have been merged into the number it annotates. No such key means the document transcribed cleanly.

  Paramètres, retour & exemple (1)

  Paramètres

  • document_id · string · requis
    Document id from list_government_documents or search_documents.

  Exemple d'appel

  {"name": "get_document", "arguments": {"document_id": "texte"}}

  Exemple de retour

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

• get_government_info≈ 197 tokens

  Get a tracked government's profile: name, location, and meeting categories.

  Paramètres, retour & exemple (2)

  Paramètres

  • government_id · string · requis
    The account_id of the government.
  • include_weekly_summary · boolean · optionnel
    If true, include the AI-generated weekly digest (markdown). Default false.

  Exemple d'appel

  {"name": "get_government_info", "arguments": {"government_id": "texte"}}

  Exemple de retour

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

• get_government_stats≈ 233 tokens

  Get meeting-activity stats for a government over a recent window. Returns total meeting count, a per-day activity map, and a breakdown of meeting categories — useful for "how active has X been lately?" questions.

  Paramètres, retour & exemple (2)

  Paramètres

  • days · integer · optionnel
    Look-back window in days (1-365).
  • government_id · string · requis
    account_id of the government, or 'all' for corpus-wide stats.

  Exemple d'appel

  {"name": "get_government_stats", "arguments": {"government_id": "texte"}}

  Exemple de retour

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

• get_meeting≈ 224 tokens

  Get a single meeting's full AI summary and topics. Set `include_transcript=true` to also retrieve the complete transcript text for direct quotation. Returns an error object if the meeting is not found.

  Paramètres, retour & exemple (2)

  Paramètres

  • meeting_id · string · requis
    The meeting_id returned by a search/list tool.
  • include_transcript · boolean · optionnel
    If true, also fetch the full meeting transcript (can be long). Default false.

  Exemple d'appel

  {"name": "get_meeting", "arguments": {"meeting_id": "texte"}}

  Exemple de retour

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

• list_government_documents≈ 368 tokens

  List a government's adopted plan and budget documents. Each entry carries `covers` — every general-plan element that document answers for. A city that publishes one bound general plan satisfies all eight with the same PDF, so do not conclude an element is unpublished because no entry is named after it. `status` says what the entry offers: `converted` is searchable and readable; `superseded` is a retired edition, still stored but not searchable; and **`failed` means we hold this document and could not read it — it is not evidence the city published nothing.** Cite `source_url` in that case; it is always the city's own copy. An `availability` block appears ONLY when something is wrong with a document, and `availability.reason` says what. No `availability` key means there is nothing to report.

  Paramètres, retour & exemple (2)

  Paramètres

  • government_id · string · requis
    account_id from find_local_governments.
  • include_superseded · boolean · optionnel
    Also include prior editions retired by a newer document.

  Exemple d'appel

  {"name": "list_government_documents", "arguments": {"government_id": "texte"}}

  Exemple de retour

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

• list_recent_meetings≈ 476 tokens

  Browse meetings newest-first, optionally filtered by government, type, topic, or date. Use this for "what are the most recent meetings" or to page through a government's history. For topical questions, prefer `search_meetings_semantic`.

  Paramètres, retour & exemple (7)

  Paramètres

  • page · integer · optionnel
    1-based page number for older results.
  • limit · integer · optionnel
    Meetings per page (1-25).
  • topic · ? · optionnel
    Optional topic filter — a topic name from discover_meeting_vocabulary, e.g. 'Affordable Housing'.
  • end_date · ? · optionnel
    Optional latest date, MM-DD-YYYY.
  • start_date · ? · optionnel
    Optional earliest date, MM-DD-YYYY.
  • category_tag · ? · optionnel
    Optional meeting-type filter — an opaque category_tag from discover_meeting_vocabulary (not a guessable slug; don't invent it).
  • government_id · ? · optionnel
    account_id to list meetings for (from find_local_governments). Omit to list across all governments.

  Exemple d'appel

  {"name": "list_recent_meetings", "arguments": {"page": 1, "limit": 1, "topic": "texte", "end_date": "texte", "start_date": "texte", "category_tag": "texte"}}

  Exemple de retour

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

• read_document_pages≈ 311 tokens

  Read a page range of a document as markdown. Pages are transcribed from rendered pixels, so tables and scanned text come through as text. A page that could not be transcribed appears as a marked hole rather than being silently dropped — if you see one, say so instead of reading past it. Text is assembled from page windows, so `covered` may be slightly wider than what you asked for; cite the page numbers in `covered`, not `requested`.

  Paramètres, retour & exemple (3)

  Paramètres

  • last_page · integer · requis
    Last page to read. Spans longer than 40 pages are clamped to 40 from first_page.
  • first_page · integer · requis
    First page to read (1-based, as the PDF renders).
  • document_id · string · requis
    Document id from list_government_documents or search_documents.

  Exemple d'appel

  {"name": "read_document_pages", "arguments": {"last_page": 1, "first_page": 1, "document_id": "texte"}}

  Exemple de retour

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

• search_documents≈ 411 tokens

  Search adopted plan and budget documents, returning page-cited excerpts. Each hit's `text` is a short passage around the match, not the full page — call read_document_pages with the hit's `first_page` to read it in context. Every hit carries `first_page`/`last_page` and `source_url`. Quote those when citing: the page number is what makes the claim checkable against the city's own copy. This is word matching, not semantic search — try the terms a plan would actually use. Only currently-served documents are searchable, so an empty result is not evidence the government has no such policy; check list_government_documents for what is held and what could not be read. A hit with `document_complete: false` comes from a document with transcription findings. Verify it against `source_url` before quoting a number from it.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Maximum excerpts to return.
  • query · string · requis
    Words to find in plan and budget text, e.g. 'accessory dwelling unit parking'.
  • government_id · ? · optionnel
    Optional account_id to restrict the search to one government.

  Exemple d'appel

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

  Exemple de retour

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

• search_meeting_content≈ 508 tokens

  Search public meetings once across metadata and stored transcript text. Returns one card per meeting and native pagination metadata, without a total. Small current-text previews can be absent and do not establish timestamps. Text relevance can lag updates or match across untimed boundaries. Source transcripts searches stored text, including meetings without timed proof.

  Paramètres, retour & exemple (10)

  Paramètres

  • limit · integer · optionnel
  • query · string · requis
    Analyzed words; put the whole query in double quotes for an analyzed phrase.
  • topic · ? · optionnel
  • cursor · ? · optionnel
    Native next_cursor or previous_cursor from the same query and filters.
  • source · string · optionnel · all | metadata | transcripts
  • end_date · ? · optionnel
  • start_date · ? · optionnel
  • category_tag · ? · optionnel
  • government_id · ? · optionnel
  • government_ids · ? · optionnel

  Exemple d'appel

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

  Exemple de retour

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

• search_meeting_transcript≈ 258 tokens

  Use unified stored-text search inside one currently public meeting. Returns an optional current-text preview, without resolving timing. A text match can lack a literal preview; use get_meeting(include_transcript=true) for full source retrieval. This does not run a separate local scan or fuzzy passage ranking.

  Paramètres, retour & exemple (2)

  Paramètres

  • query · string · requis
    Analyzed words or a whole quoted phrase.
  • meeting_id · string · requis
    Canonical meeting_id returned by a search/list tool.

  Exemple d'appel

  {"name": "search_meeting_transcript", "arguments": {"query": "texte", "meeting_id": "texte"}}

  Exemple de retour

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

• search_meetings_semantic≈ 681 tokens

  Find AI summaries by meaning; use search_meeting_content for stored words. Results carry relevance_score and a summary preview. Narrow with government, category_tag, topic or dates; get_meeting retrieves the full summary.

  Paramètres, retour & exemple (10)

  Paramètres

  • limit · integer · optionnel
    Max meetings to return (1-25).
  • query · string · requis
    What to search for in plain language, e.g. 'short-term rental regulations' or 'police budget overtime'.
  • topic · ? · optionnel
    Optional topic filter — a topic name from discover_meeting_vocabulary, e.g. 'Affordable Housing'. Restricts to meetings that discussed it.
  • end_date · ? · optionnel
    Optional latest meeting date, MM-DD-YYYY.
  • min_score · ? · optionnel
    Optional semantic relevance floor 0-1 (default 0.4). Raise to return only strong matches; lower to widen recall.
  • match_type · string · optionnel
    Semantic only; use search_meeting_content for keyword searches.
  • start_date · ? · optionnel
    Optional earliest meeting date, MM-DD-YYYY.
  • category_tag · ? · optionnel
    Optional meeting-type filter — an opaque category_tag from discover_meeting_vocabulary (not a guessable slug).
  • government_id · ? · optionnel
    Optional account_id (from find_local_governments) to restrict the search to one government.
  • government_ids · ? · optionnel
    Optional list of account_ids to search across several governments at once (e.g. to compare cities). Overrides government_id.

  Exemple d'appel

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

  Exemple de retour

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

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://api.openpublica.com/mcp