Trust, freshness, policy, and discovery layer for public MCP servers.
Déduit des transports déclarés par cette annonce (streamable-http). Un client absent de cette liste n’est pas écarté pour autant — c’est simplement quelque chose que Forge ne peut pas confirmer.
La vérification confirme l’identité de l’éditeur (la propriété du dépôt), pas la sûreté du code. L’analyse de sécurité couvre les CVE connues et les scripts d’installation suspects.
Lu depuis un véritable échange MCP initialize → tools/list contre l’endpoint déclaré. Aucun outil n’a été invoqué — tools/list est l’appel d’introspection en lecture seule que le protocole prévoit pour cela. Cela reflète ce que le serveur annonçait à cet instant ; un endpoint hébergé n’est figé sur aucune version et peut changer sans préavis.
https://verify.sentinelsignal.io/mcp22 outils · 201 mssearchChatGPT-compatible read-only search alias. Returns MCP server results with id, title, and url.ChatGPT-compatible read-only search alias. Returns MCP server results with id, title, and url.
| Paramètre | Type | Description |
|---|---|---|
| query* | string | Search query such as healthcare MCP, web search MCP, ChatGPT-compatible MCPs, or OAuth MCP servers. |
| limit | integer | Maximum number of search results to return. |
fetchChatGPT-compatible read-only fetch alias. Returns a full MCP server item with id, title, text, url, and metadata.ChatGPT-compatible read-only fetch alias. Returns a full MCP server item with id, title, text, url, and metadata.
| Paramètre | Type | Description |
|---|---|---|
| id* | string | Canonical MCP server identifier in namespace/name format. |
search_serversSearch and rank MCP servers by capability, auth preference, client target, and risk tolerance.Search and rank MCP servers by capability, auth preference, client target, and risk tolerance.
| Paramètre | Type | Description |
|---|---|---|
| capabilities | array | Normalized capability taxonomy terms such as healthcare, search, read, exec, files, oauth, or prompts. |
| auth_preference | string | Preferred auth mode. Use unauthenticated when the agent must avoid login flows. |
| client_target | string | Optional target client or integration surface. |
| risk_tolerance | string | How much tool-surface risk is acceptable. |
| query | string | Optional free-text query to bias ranking toward a specific use case or domain. |
| limit | integer | Maximum number of ranked candidates to return. |
recommend_serversRecommend MCP servers for a plain-language task and return ranked matches with install config.Recommend MCP servers for a plain-language task and return ranked matches with install config.
| Paramètre | Type | Description |
|---|---|---|
| task* | string | Plain-language task description such as 'I need an MCP for healthcare denial scoring in OpenAI connectors'. |
| capabilities | array | Optional explicit capability constraints that override or extend the inferred task capabilities. |
| auth_preference | string | Preferred auth mode. |
| client_target | string | Optional target client or integration surface. |
| risk_tolerance | string | How much tool-surface risk is acceptable. |
| limit | integer | Maximum number of recommendations to return. |
get_server_reportReturn the full machine-readable verify report for a specific MCP server identifier.Return the full machine-readable verify report for a specific MCP server identifier.
| Paramètre | Type | Description |
|---|---|---|
| identifier* | string | Canonical server identifier in namespace/name format. |
compare_serversCompare up to four MCP servers side by side across score, verdict, auth, tool count, prompts/resources, and freshness.Compare up to four MCP servers side by side across score, verdict, auth, tool count, prompts/resources, and freshness.
| Paramètre | Type | Description |
|---|---|---|
| identifiers* | array | Canonical server identifiers in namespace/name format. |
route_taskChoose the best MCP server/tools for a task. Use decide_agent_call when evaluating one specific attempted tool call.Choose the best MCP server/tools for a task. Use decide_agent_call when evaluating one specific attempted tool call.
| Paramètre | Type | Description |
|---|---|---|
| task* | string | Task the agent wants to perform. |
| candidate | string | Optional namespace/name server identifier to evaluate directly. |
| capabilities | array | Optional capability constraints such as healthcare, search, database, read, or write. |
| client_target | string | — |
| max_risk | string | Maximum allowed tool risk. |
| requires_oauth | boolean | — |
| no_write_without_approval | boolean | — |
| max_freshness_hours | number | — |
decide_agent_callVerify Gateway decision point. Decide whether this agent may call this tool, with this payload, for this user, right now. Writes an audit-ledger decision event.Verify Gateway decision point. Decide whether this agent may call this tool, with this payload, for this user, right now. Writes an audit-ledger decision event.
| Paramètre | Type | Description |
|---|---|---|
| agent_id* | string | — |
| user_id* | string | — |
| server_id* | string | Server identifier in namespace/name format. |
| tool* | string | — |
| action | string | — |
| mandate_id | string | Optional Verify Mandate key or id. |
| payload_classification | array | — |
| requested_cost | number | — |
| max_cost | number | — |
| approval_token_present | boolean | — |
| client | string | — |
| max_risk | string | — |
| requires_oauth | boolean | — |
| no_write_without_approval | boolean | — |
| max_freshness_hours | number | — |
| max_runtime_seconds | integer | — |
| audit_context | object | — |
create_mandateCreate a Verify Mandate: signed delegated authority for an agent/user/server scope, budget, validity window, and tool constraints.Create a Verify Mandate: signed delegated authority for an agent/user/server scope, budget, validity window, and tool constraints.
| Paramètre | Type | Description |
|---|---|---|
| user_id* | string | — |
| agent_id* | string | — |
| server_id | string | — |
| scope* | string | — |
| budget_limit | number | — |
| valid_until | string | — |
| requires_human_approval | boolean | — |
| signature | string | — |
| constraints | object | — |
| metadata | object | — |
get_evidence_packReturn Verify Ledger evidence packs with invocations, hash-chained audit events, decisions, outcomes, mandates, and cost summaries.Return Verify Ledger evidence packs with invocations, hash-chained audit events, decisions, outcomes, mandates, and cost summaries.
| Paramètre | Type | Description |
|---|---|---|
| server_id | string | — |
| agent_id | string | — |
| user_id | string | — |
| limit | integer | — |
compile_docsGenerate agent-readable MCP artifacts from product docs: server card, llms.txt, tool schemas, examples, policy metadata, score preview, and hosted docs page.Generate agent-readable MCP artifacts from product docs: server card, llms.txt, tool schemas, examples, policy metadata, score preview, and hosted docs page.
| Paramètre | Type | Description |
|---|---|---|
| title* | string | — |
| source_type | string | — |
| source_url | string | — |
| openapi_spec | object | — |
| markdown_docs | string | — |
| postman_collection | object | — |
| website_docs | string | — |
| server_identifier | string | — |
| policy_metadata | object | — |
| metadata | object | — |
export_policyExport a JSON TrustOps policy for one MCP server with allow, blocked tools, required scopes, freshness, and approval gates.Export a JSON TrustOps policy for one MCP server with allow, blocked tools, required scopes, freshness, and approval gates.
| Paramètre | Type | Description |
|---|---|---|
| identifier* | string | Canonical server identifier in namespace/name format. |
| client | string | — |
| max_risk | string | — |
| requires_oauth | boolean | — |
| no_write_without_approval | boolean | — |
| max_freshness_hours | number | — |
get_subscription_optionsReturn alert types, subscription channels, watch scopes, and existing subscription endpoints.Return alert types, subscription channels, watch scopes, and existing subscription endpoints.
Aucun schéma d’entrée n’a été publié pour cet outil.
get_gateway_optionsReturn Verify Gateway semantics, /v1/route versus /v1/decide guidance, mandate inputs, ledger evidence hooks, and decision fields.Return Verify Gateway semantics, /v1/route versus /v1/decide guidance, mandate inputs, ledger evidence hooks, and decision fields.
Aucun schéma d’entrée n’a été publié pour cet outil.
get_hosting_optionsReturn Verify Hosted MCP runtime/sandbox hosting capabilities, controls, and endpoints.Return Verify Hosted MCP runtime/sandbox hosting capabilities, controls, and endpoints.
Aucun schéma d’entrée n’a été publié pour cet outil.
list_agentsAgent Sprawl Radar: list discovered AI agents, MCP servers, bots, workflows, risk levels, and owners.Agent Sprawl Radar: list discovered AI agents, MCP servers, bots, workflows, risk levels, and owners.
| Paramètre | Type | Description |
|---|---|---|
| risk_level | string | — |
| limit | integer | — |
get_agentAgent Sprawl Radar: return one agent with tools, data access, findings, drift, and recommended action.Agent Sprawl Radar: return one agent with tools, data access, findings, drift, and recommended action.
| Paramètre | Type | Description |
|---|---|---|
| agent_id* | string | — |
score_agentAgent Sprawl Radar: score a normalized agent payload or an existing registry agent.Agent Sprawl Radar: score a normalized agent payload or an existing registry agent.
| Paramètre | Type | Description |
|---|---|---|
| agent_id | string | — |
| agent | object | — |
explain_agent_riskAgent Sprawl Radar: explain risk findings and the recommended action for one registry agent.Agent Sprawl Radar: explain risk findings and the recommended action for one registry agent.
| Paramètre | Type | Description |
|---|---|---|
| agent_id* | string | — |
list_high_risk_agentsAgent Sprawl Radar: list high and critical risk agents for review.Agent Sprawl Radar: list high and critical risk agents for review.
| Paramètre | Type | Description |
|---|---|---|
| limit | integer | — |
get_drift_reportAgent Sprawl Radar: return agent drift events across latest snapshots.Agent Sprawl Radar: return agent drift events across latest snapshots.
| Paramètre | Type | Description |
|---|---|---|
| agent_id | string | — |
| limit | integer | — |
generate_remediation_planAgent Sprawl Radar: generate deterministic remediation steps for risky or drifting agents.Agent Sprawl Radar: generate deterministic remediation steps for risky or drifting agents.
| Paramètre | Type | Description |
|---|---|---|
| agent_id* | string | — |
22 outils sur 22 ont publié une description.
Les noms et descriptions d’outils sont écrits par l’éditeur et affichés tels quels, comme du texte inerte. Ce sont les chaînes qu’un client MCP transmet à un modèle, alors Forge y recherche des motifs d’injection de prompt — tout constat apparaît avec l’analyse de sécurité ci-dessus. « Privilégié » est une correspondance de mot-clé sur le nom de l’outil, pas un audit de ce qu’il fait : un nom anodin peut tout de même tout faire.
Trust, freshness, policy, and discovery layer for public MCP servers.
Les noms cliquables ouvrent l’index Forge de toutes les entrées observées exposant cet outil. Parcourir tous les outils indexés.
Cette entrée ne publie aucun paquet npm : Forge n'a donc pas d'arbre de dépendances pour elle. C'est une lacune de couverture — pas une affirmation qu'elle n'a aucune dépendance.