Trust, freshness, policy, and discovery layer for public MCP servers.
Abgeleitet aus den Transporten, die dieser Eintrag deklariert (streamable-http). Ein Client, der hier nicht steht, ist damit nicht ausgeschlossen — Forge kann ihn nur nicht bestätigen.
Die Verifizierung bestätigt die Identität des Publishers (die Inhaberschaft am Repo), nicht die Sicherheit des Codes. Der Sicherheits-Scan deckt bekannte CVEs und verdächtige Installationsskripte ab.
Aus einem echten MCP-Handshake initialize → tools/list gegen den deklarierten Endpunkt gelesen. Es wurde nie ein Tool aufgerufen — tools/list ist der lesende Introspektionsaufruf, den das Protokoll dafür vorsieht. Es spiegelt wider, was der Server in diesem Moment angeboten hat; ein gehosteter Endpunkt ist an keine Version gebunden und kann sich ohne Ankündigung ändern.
https://verify.sentinelsignal.io/mcp22 Tools · 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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| 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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| 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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| 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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| 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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| 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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| 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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| 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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| 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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| 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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| 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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| 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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| 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.
Für dieses Tool wurde kein Eingabeschema veröffentlicht.
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.
Für dieses Tool wurde kein Eingabeschema veröffentlicht.
get_hosting_optionsReturn Verify Hosted MCP runtime/sandbox hosting capabilities, controls, and endpoints.Return Verify Hosted MCP runtime/sandbox hosting capabilities, controls, and endpoints.
Für dieses Tool wurde kein Eingabeschema veröffentlicht.
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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| 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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| 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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| 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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| 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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| limit | integer | — |
get_drift_reportAgent Sprawl Radar: return agent drift events across latest snapshots.Agent Sprawl Radar: return agent drift events across latest snapshots.
| Parameter | Typ | Beschreibung |
|---|---|---|
| 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.
| Parameter | Typ | Beschreibung |
|---|---|---|
| agent_id* | string | — |
22 von 22 Tools haben eine Beschreibung veröffentlicht.
Tool-Namen und -Beschreibungen stammen vom Publisher und werden wortgetreu als inerter Text angezeigt. Es sind die Zeichenketten, die ein MCP-Client an ein Modell übergibt, deshalb prüft Forge sie auf Prompt-Injection-Muster — jeder Befund erscheint oben beim Sicherheits-Scan. „Privilegiert“ ist ein Schlagwort-Treffer im Tool-Namen, keine Prüfung dessen, was das Tool tut: ein harmlos klingender Name kann trotzdem alles tun.
Trust, freshness, policy, and discovery layer for public MCP servers.
Verlinkte Namen öffnen den Forge-Index aller Einträge, bei denen dieses Tool beobachtet wurde. Alle indexierten Tools durchsuchen.
Dieser Eintrag veröffentlicht kein npm-Paket, daher hat Forge keinen Abhängigkeitsbaum dafür. Das ist eine Lücke in der Abdeckung — keine Aussage, dass er keine Abhängigkeiten hat.