ai.overwing/mcp

Est-ce que ai.overwing/mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.overwing/mcp » 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 41 outils

• atlas_agents≈ 282 tokens

  Browse or search Overwing Atlas, the registry of AI crawlers, fetchers and browser agents: name, operator, user-agent tokens, Web Bot Auth key directory, robots.txt behaviour, and (with Atlas Pro or Team) purpose class, verification, evasion flags and traffic shares. Filter by free text, purpose (training, search, browser, coding), operator, or verification. Needs an organization key.

  Paramètres, retour & exemple (5)

  Paramètres

  • q · string · optionnel
    Free text over name, operator, user agents, description
  • limit · integer · optionnel
  • purpose · string · optionnel
    Purpose substring, e.g. training, search, browser, fetcher, coding
  • operator · string · optionnel
  • verification · string · optionnel
    e.g. 'Web Bot Auth', 'spoofable', 'Unattributable'

  Exemple d'appel

  {"name": "atlas_agents", "arguments": {"q": "texte", "limit": 1, "purpose": "texte", "operator": "texte", "verification": "texte"}}

  Exemple de retour

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

• atlas_list_registrations≈ 126 tokens

  The agents this organization has registered in Overwing Atlas, newest first, each with its status (pending_verification, pending_review, published, rejected) and, while unverified, the value to publish at the domain. Needs an organization key.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "atlas_list_registrations", "arguments": {}}

  Exemple de retour

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

• atlas_lookup≈ 234 tokens

  Say what a User-Agent string claims to be and whether the claim can be trusted, from the Overwing Atlas registry of AI crawlers, fetchers and browser agents. Returns the claimed agent, operator, purpose class, verification method (Web Bot Auth signature, user-agent string only, or unattributable) and a trust note. Works with no API key: 10 lookups a day. With a key, metered per day by Atlas tier: free 100, Pro 10,000, Team 100,000. Use it when deciding whether to serve, block, or pay-gate a request, or to understand who is hitting a site.

  Paramètres, retour & exemple (1)

  Paramètres

  • user_agent · string · requis
    The User-Agent header value to identify

  Exemple d'appel

  {"name": "atlas_lookup", "arguments": {"user_agent": "texte"}}

  Exemple de retour

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

• atlas_register_agent≈ 581 tokens

  Add an agent or crawler you operate to the Overwing Atlas registry, free, so a site that looks up its User-Agent learns who runs it. Give the agent's name, the operator (the company or person running it), the operator's domain, and the token the User-Agent carries (the product name, such as AcmeBot). The answer carries one value to publish at that domain, as a DNS TXT record or as a file under /.well-known, to prove control of it; then call atlas_verify_registration. A token may not match, contain, or sit inside one already in the registry. This proves control of the domain, not that any given request is yours: the entry is listed as user-agent only unless key_directory_url is a Web Bot Auth key directory on that domain. Only register agents you or your operator actually run. Needs an organization key.

  Paramètres, retour & exemple (10)

  Paramètres

  • name · string · requis
    The agent's name, e.g. AcmeBot
  • domain · string · requis
    The operator's domain, e.g. acme.com. Control of it must be proved
  • tokens · array · requis
    The product name the User-Agent carries, e.g. ["AcmeBot"]
  • purpose · string · optionnel · training_crawl | search_index | user_fetch | browser_agent | coding_agent | api_agent | other
  • operator · string · requis
    The company or person that runs the agent
  • policy_url · string · optionnel
    An https page describing the agent
  • user_agent · string · optionnel
    The full User-Agent string the agent sends; it must contain a token
  • description · string · optionnel
  • key_directory_url · string · optionnel
    A Web Bot Auth key directory on the operator's domain
  • follows_robots_txt · boolean · optionnel

  Exemple d'appel

  {"name": "atlas_register_agent", "arguments": {"name": "texte", "domain": "texte", "tokens": [], "operator": "texte"}}

  Exemple de retour

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

• atlas_summary≈ 146 tokens

  Public numbers from Overwing Atlas: registry counts by purpose and verification, published browser-agent traffic shares, sector field-scan headlines (e.g. how many OSINT sites carry AI-crawler rules or any agent-payable surface), and the summary of the Agent Consumers report on what agents actually spend. No key needed.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "atlas_summary", "arguments": {}}

  Exemple de retour

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

• atlas_verify_registration≈ 204 tokens

  Look for the proof at the operator's domain: the DNS TXT record or the file that atlas_register_agent asked for. Found: the entry is published in the registry, or held for a person when the operator name already belongs to someone. Not found: an error saying what was looked for; DNS changes can take a few minutes, and calling again is safe. Needs an organization key.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    The registration id from atlas_register_agent

  Exemple d'appel

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

  Exemple de retour

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

• atlas_withdraw_registration≈ 167 tokens

  Withdraw a registration. A published entry leaves the registry, so lookups stop naming the agent; an unfinished request is abandoned. This cannot be undone: register again to put it back. Needs an organization key.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    The registration id from atlas_register_agent

  Exemple d'appel

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

  Exemple de retour

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

• beacon_report≈ 222 tokens

  The report for a check started with beacon_start. The first call runs the check. With an Overwing key on the connection: score (0 to 100), verdict (yes, partly, no), the find / read / use answers, every check with what was found and a fix when it did not pass, and top_fixes ranked by value. With no key, the summary of the same report: score, verdict, the three answers and the first fix (access=summary). Answers 202 while the check is running (ask again in a few seconds). No key needed for the summary.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    The check id from beacon_start

  Exemple d'appel

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

  Exemple de retour

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

• beacon_sample≈ 106 tokens

  A real Overwing Beacon report, free: the check of overwing.ai itself, refreshed daily. Read it to see exactly what a full report holds before starting a check. No key needed.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "beacon_sample", "arguments": {}}

  Exemple de retour

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

• beacon_start≈ 348 tokens

  Overwing Beacon answers one question about a site: is this product reachable by agents? It checks robots.txt rules for AI agents, llms.txt, the sitemap, the MCP server card, hosted MCP endpoint and MCP Registry listing, the A2A agent card, OpenAPI discovery, and how the home page reads to a model, then returns three answers (find, read, use), a score and the fixes worth making. This tool starts a check and returns its id; it is free. Then call beacon_report with the id, which runs the check (about twenty seconds). With an Overwing key on the connection beacon_report returns the full report and the check is saved to that dashboard; with no key it returns the summary: the score, the three answers and the first fix. A key is free (POST /api/v1/signup). An agent with a wallet and no account can instead pay $1 in USDC over x402 and get the full report in one call: GET /api/x402/beacon?url=<site>. Call beacon_sample to see a real report in full. No key needed.

  Paramètres, retour & exemple (1)

  Paramètres

  • url · string · requis
    The site to check: a domain (example.com) or an https URL. Public sites only.

  Exemple d'appel

  {"name": "beacon_start", "arguments": {"url": "texte"}}

  Exemple de retour

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

• create_account≈ 335 tokens

  Create an Overwing account for yourself, with no email: an organization and an API key, returned once. Nothing is sent to anyone. Use it when you have no key and nobody has given you one; do not create a second account if you already have a key (whoami says which account a key belongs to). The key is the account, so store it at once: with no email there is no reset link. It starts at 50 evaluations a day with Beacon summaries; proving a domain (prove_domain, verify_domain) raises that to the normal free limits and full Beacon reports, and makes a lost key recoverable. This server does not keep the key: send it as Authorization: Bearer on the MCP connection for the tools that need one. Tell the person you work for that you made the account and where the key is kept. No key needed.

  Paramètres, retour & exemple (2)

  Paramètres

  • org_name · string · optionnel
    A name for the account, e.g. the agent's name
  • use_for_session · boolean · optionnel
    Ignored here. The hosted server has no session and never holds a key; it exists so calls written for the npm package still validate.

  Exemple d'appel

  {"name": "create_account", "arguments": {"org_name": "texte", "use_for_session": true}}

  Exemple de retour

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

• create_rule_set≈ 470 tokens

  Create a custom rule set with 1 to 25 rules. Each rule is a choice (pick one option), score (position on an ordered scale), or noul (yes/no) question with a fail condition, optional review threshold, weight, and action (block, redact, or review) that callers should take when it fails. Rule instructions may reference `context.*` fields that callers pass with each evaluation. Needs an organization key.

  Paramètres, retour & exemple (4)

  Paramètres

  • name · string · requis
  • slug · string · requis
  • rules · array · requis
  • description · string · optionnel

  Exemple d'appel

  {"name": "create_rule_set", "arguments": {"name": "texte", "slug": "texte", "rules": []}}

  Exemple de retour

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

• evaluate≈ 518 tokens

  Works with no API key: 10 evaluations a day, inputs up to 2,000 characters, and the text is not stored. With a key: 250 a day and up, inputs up to 100,000 characters, and your own rule sets. Score any text (typically an LLM's output) against an Overwing rule set. The text can be in any language; tested in Spanish, Portuguese, French, German, Japanese, Chinese, Korean, Arabic and Hindi. Results come back in English. Returns an aggregate verdict of pass, fail, or review, a recommended_action (block, redact, review, or allow), and per-rule answers with probability, confidence, and the rule's action. Act on recommended_action: block means do not send, redact means remove the flagged content and resend, review means ask a human or a slower model, allow means proceed. Prebuilt sets: 'content-safety' (toxicity, PII, self-harm, sexual content, severity) and 'outbound-message', which also takes a context object (recipient, channel, owns_contact_info) so PII that the recipient already owns is not flagged.

  Paramètres, retour & exemple (5)

  Paramètres

  • input · string · requis
    The text to evaluate, in any language
  • store · boolean · optionnel
    With a key: false runs the check without keeping the input text or the context (the verdict and metadata are still recorded). Without a key the text is never stored.
  • context · object · optionnel
    Facts the rules may reference: recipient, channel, whether you own the data, sender, purpose. Sent to the model alongside the text (max 8 KB). Use the 'outbound-message' rule set to have it honoured.
  • metadata · object · optionnel
    Opaque data stored with the evaluation and echoed in webhooks (max 8 KB)
  • rule_set · string · optionnel
    Rule set slug

  Exemple d'appel

  {"name": "evaluate", "arguments": {"input": "texte"}}

  Exemple de retour

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

• evaluate_batch≈ 323 tokens

  Score up to 50 texts against one rule set in a single call. Each item counts as one evaluation. Returns a summary plus per-item verdicts; items can fail independently. Needs an organization key.

  Paramètres, retour & exemple (4)

  Paramètres

  • items · array · requis
  • store · boolean · optionnel
    False runs every item without keeping its input text or context
  • context · object · optionnel
    Facts the rules may reference: recipient, channel, whether you own the data, sender, purpose. Sent to the model alongside the text (max 8 KB). Use the 'outbound-message' rule set to have it honoured.
  • rule_set · string · optionnel

  Exemple d'appel

  {"name": "evaluate_batch", "arguments": {"items": []}}

  Exemple de retour

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

• feedback≈ 271 tokens

  Send one message to the people who run Overwing: a verdict you think was wrong, an error you could not act on, a payment you could not make, a tool that did not do what its description says. Read by a person, not answered automatically; give a contact if you want an answer. No key needed.

  Paramètres, retour & exemple (4)

  Paramètres

  • about · string · optionnel
    What it concerns: a tool name, a path, a product. Optional.
  • contact · string · optionnel
    Where an answer can reach you or the person you work for: an email, a URL, an agent name. Optional.
  • message · string · requis
    What happened and what you expected.
  • evaluation_id · string · optionnel
    The id of the evaluation in question, if any.

  Exemple d'appel

  {"name": "feedback", "arguments": {"message": "texte"}}

  Exemple de retour

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

• get_evaluation≈ 95 tokens

  Fetch a stored evaluation by id, including the original input and per-rule results. Needs an organization key.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis

  Exemple d'appel

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

  Exemple de retour

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

• get_rule_set≈ 102 tokens

  Fetch a rule set with its full rule definitions. Use 'content-safety' as a worked example when writing your own. Needs an organization key.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis

  Exemple d'appel

  {"name": "get_rule_set", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• get_usage≈ 79 tokens

  Daily usage, remaining quota for today, and plan limits. Needs an organization key.

  Paramètres, retour & exemple (1)

  Paramètres

  • days · integer · optionnel

  Exemple d'appel

  {"name": "get_usage", "arguments": {"days": 1}}

  Exemple de retour

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

• list_evaluations≈ 130 tokens

  List recent evaluations, newest first, with optional verdict and rule set filters. Use next_cursor to page. Needs an organization key.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
  • cursor · string · optionnel
  • verdict · string · optionnel · pass | fail | review
  • rule_set · string · optionnel

  Exemple d'appel

  {"name": "list_evaluations", "arguments": {"limit": 1, "cursor": "texte", "verdict": "pass", "rule_set": "texte"}}

  Exemple de retour

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

• list_plans≈ 67 tokens

  Public plan catalog: prices, daily limits, and per-minute burst limits. No API key needed.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_plans", "arguments": {}}

  Exemple de retour

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

• list_rule_sets≈ 82 tokens

  List the prebuilt and custom rule sets available to this organization. Needs an organization key.

  Paramètres, retour & exemple (1)

  Paramètres

  • include_inactive · boolean · optionnel

  Exemple d'appel

  {"name": "list_rule_sets", "arguments": {"include_inactive": true}}

  Exemple de retour

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

• preflight_check≈ 697 tokens

  Call this before signing any Solana transaction. Overwing Preflight simulates the unsigned transaction against the chain as it is now, works out what it would take from the wallet you name (SOL, tokens, and control of its token accounts) and answers allow or refuse against your policy, with every reason. Sign only if decision is "allow". Treat a refusal, an error, or anything else as do not sign. A verdict describes one moment and covers a transaction that lands within about two minutes, so sign and send at once or check again. This tool takes the serialized transaction and a policy; it never needs a private key and must never be given one. One check counts as one evaluation. Needs an organization key.

  Paramètres, retour & exemple (2)

  Paramètres

  • policy · object · requis
    What the transaction may take from the wallet. Anything the policy does not allow is refused. Give max_sol_out or max_sol_out_lamports, never both.
  • transaction · string · requis
    The serialized Solana transaction in base64, legacy or v0, signed or unsigned. Signatures are ignored.

  Exemple d'appel

  {"name": "preflight_check", "arguments": {"policy": {}, "transaction": "texte"}}

  Exemple de retour

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

• preflight_overview≈ 133 tokens

  The reference for Overwing Preflight: every policy field, every reason code a refusal can carry, what a verdict does and does not promise, the price, and the terms of the guarantee. Read it once before the first preflight_check. No key needed.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "preflight_overview", "arguments": {}}

  Exemple de retour

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

• preflight_payment≈ 380 tokens

  Call this with the 402 you were given, before signing an x402 payment. It reads the terms (network, asset, amount, payee, timeout, resource) and answers allow, review or refuse with reasons: the terms against your policy, the payee against x402-list's directory (verified delivery, recorded settlements, buyers, shared payout addresses) and the server's own /.well-known/x402 manifest, and the price against what is recorded for that endpoint. Not a simulation and not a guarantee. Sign only on allow; on review, ask the person you work for. No key needed for a few checks a day.

  Paramètres, retour & exemple (4)

  Paramètres

  • policy · object · optionnel
    Optional: max_per_call_usd (default 0.05), new_payee_max_usd (0.01), allowed_networks, allowed_payees, blocked_payees, allow_testnets, max_price_drift (0.25).
  • network · string · optionnel
    The CAIP-2 network you would pay on, e.g. eip155:8453. Optional.
  • requested_url · string · optionnel
    The URL you asked for and got the 402 from.
  • payment_required · string · requis
    The PAYMENT-REQUIRED header value of the 402 (base64), or its decoded JSON as a string.

  Exemple d'appel

  {"name": "preflight_payment", "arguments": {"payment_required": "texte"}}

  Exemple de retour

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

• preflight_record≈ 122 tokens

  Everything Preflight has said and how it held up: counts of verdicts and misses, every miss with what the chain showed, the latest verdicts, and what the guarantee's reserve holds. Read it before deciding whether to rely on Preflight. No key needed.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "preflight_record", "arguments": {}}

  Exemple de retour

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

• preflight_report≈ 240 tokens

  After a transaction that Preflight allowed has landed, report its signature. Preflight reads the landed transaction from the chain and says whether the allow held: not_a_miss, or miss when it took more from the wallet than the policy permitted. The outcome is published. A covered miss is paid to the wallet in the verdict, never to whoever reported it. No key needed.

  Paramètres, retour & exemple (2)

  Paramètres

  • id · string · requis
    The verdict id from preflight_check
  • signature · string · requis
    The landed transaction's signature in base58

  Exemple d'appel

  {"name": "preflight_report", "arguments": {"id": "texte", "signature": "texte"}}

  Exemple de retour

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

• preflight_verdict≈ 165 tokens

  The public record of one Preflight verdict: its decision, reason codes, the programs the transaction would run, the transaction's digest, our signature, and every landed transaction reported against it. Never the wallet, the amounts or the transaction. No key needed.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    The verdict id from preflight_check

  Exemple d'appel

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

  Exemple de retour

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

• prove_domain≈ 216 tokens

  Begin proving that your account controls a domain. For an account with no email the domain stands in for one: it raises the limits to the normal free tier, opens full Beacon reports, and lets a lost key be replaced. Returns one value to publish at the domain, as a DNS TXT record or as a file under /.well-known; then call verify_domain. One domain belongs to one account. Calling again for the same domain returns the same value. Needs an organization key.

  Paramètres, retour & exemple (1)

  Paramètres

  • domain · string · requis
    A domain you or your operator controls, e.g. acme.com

  Exemple d'appel

  {"name": "prove_domain", "arguments": {"domain": "texte"}}

  Exemple de retour

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

• tower_capabilities≈ 112 tokens

  List the operations this agent is allowed to call, each with the JSON Schema its input must match and its compensating operation. Call this first; build inputs from the schema rather than guessing. Needs an agent key.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "tower_capabilities", "arguments": {}}

  Exemple de retour

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

• tower_compensate≈ 162 tokens

  Run the compensating operation for an executed action, for example cancel the order that create_order made. Runs once; repeating it returns the first outcome. Needs an agent key.

  Paramètres, retour & exemple (1)

  Paramètres

  • action_id · string · requis
    The executed action's id (a UUID)

  Exemple d'appel

  {"name": "tower_compensate", "arguments": {"action_id": "texte"}}

  Exemple de retour

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

• tower_create_agent≈ 337 tokens

  Create a scoped agent identity and its key. Needs an organization key. Scope it to the operations the agent needs (for example create_order) rather than * where you can. The key (ow_agent_...) is returned once, in this result, and this server does not keep it: store it, and send it as the Authorization bearer on a connection used for the agent tools (tower_capabilities, tower_decide, tower_submit_action, tower_get_action, tower_compensate, tower_get_receipt, tower_verify_receipts). Revoke with tower_revoke_agent.

  Paramètres, retour & exemple (3)

  Paramètres

  • name · string · requis
    A name a person will recognise in the review queue, e.g. order-intake-bot
  • scopes · array · requis
    Operation names this agent may call, or ["*"] for all
  • use_for_session · boolean · optionnel
    Ignored here. The hosted server has no session and never holds a key; it exists so calls written for the npm package still validate.

  Exemple d'appel

  {"name": "tower_create_agent", "arguments": {"name": "texte", "scopes": []}}

  Exemple de retour

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

• tower_decide≈ 180 tokens

  Ask Tower how it would rule on an operation without doing anything: auto (would execute), review (a person must approve), or reject. Returns the score, the reason, and each policy question's answer. No side effects. Needs an agent key.

  Paramètres, retour & exemple (2)

  Paramètres

  • input · object · requis
    The operation's input, matching its input_schema from tower_capabilities
  • operation · string · requis

  Exemple d'appel

  {"name": "tower_decide", "arguments": {"input": {}, "operation": "texte"}}

  Exemple de retour

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

• tower_get_action≈ 154 tokens

  Status and result of an action: pending, approved, executed, failed, compensated, or rejected. Use it to poll an action that is waiting on human review. Needs an agent key.

  Paramètres, retour & exemple (1)

  Paramètres

  • action_id · string · requis
    The action's id (a UUID), from tower_submit_action

  Exemple d'appel

  {"name": "tower_get_action", "arguments": {"action_id": "texte"}}

  Exemple de retour

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

• tower_get_receipt≈ 125 tokens

  Fetch one signed receipt by id or by sequence number: the payload, its hash, the previous link's hash, and the Ed25519 signature. Needs an agent key.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Receipt id or sequence number

  Exemple d'appel

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

  Exemple de retour

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

• tower_list_agents≈ 86 tokens

  List this organization's Tower agents with scopes, status and last use. Keys are never returned. Needs an organization key.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "tower_list_agents", "arguments": {}}

  Exemple de retour

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

• tower_load_template≈ 148 tokens

  Set up Overwing Tower for this organization by loading the starter workflow: email purchase order to order entry, with create_order, update_order and cancel_order against a mock IBM i system, and a starter policy. Idempotent. Needs an organization key. Returns a sample input you can submit. Next: tower_create_agent.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "tower_load_template", "arguments": {}}

  Exemple de retour

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

• tower_revoke_agent≈ 148 tokens

  Revoke an agent. Its key stops working at once and cannot be restored. Needs an organization key.

  Paramètres, retour & exemple (1)

  Paramètres

  • agent_id · string · requis
    The agent's id (a UUID), from tower_list_agents

  Exemple d'appel

  {"name": "tower_revoke_agent", "arguments": {"agent_id": "texte"}}

  Exemple de retour

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

• tower_submit_action≈ 286 tokens

  Ask Tower to perform an operation on the legacy system. Tower decides: executed (done), pending (a person must approve; poll tower_get_action, do not resubmit), or rejected (do not retry unchanged). Always send an idempotency_key that is stable for this business request, such as the source message id: repeating a key returns the original outcome instead of acting twice. Set dry_run to see the decision without executing. Needs an agent key.

  Paramètres, retour & exemple (4)

  Paramètres

  • input · object · requis
    The operation's input, matching its input_schema from tower_capabilities
  • dry_run · boolean · optionnel
  • operation · string · requis
  • idempotency_key · string · requis
    Stable per business request; reuse it on retries

  Exemple d'appel

  {"name": "tower_submit_action", "arguments": {"input": {}, "operation": "texte", "idempotency_key": "texte"}}

  Exemple de retour

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

• tower_verify_receipts≈ 134 tokens

  Recompute every hash and check every signature over a range of this organization's receipts. Reports the first break, if any. Defaults to the whole chain (up to 5,000 links per call). Needs an agent key.

  Paramètres, retour & exemple (2)

  Paramètres

  • to · integer · optionnel
  • from · integer · optionnel

  Exemple d'appel

  {"name": "tower_verify_receipts", "arguments": {"to": 1, "from": 1}}

  Exemple de retour

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

• verify_domain≈ 116 tokens

  Look for the value prove_domain asked for, at the domain. Found: the domain is the account's. Not found: an error saying what was looked for; DNS changes can take a few minutes, and calling again is safe. Needs an organization key.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "verify_domain", "arguments": {}}

  Exemple de retour

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

• whoami≈ 95 tokens

  Identify the organization and plan behind the API key on this request, the key's scope, the organization's data settings (store_inputs, retention_days), and whether billing is set up. Needs an organization key.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "whoami", "arguments": {}}

  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://overwing.ai/mcp