io.sentinelsignal/verify

Official22 tools

MCP Verify

Trust, freshness, policy, and discovery layer for public MCP servers.

Verification and discovery layer for MCP servers with trust, freshness, and policy checks.

Captured live from the server via tools/list.

search

ChatGPT-compatible read-only search alias. Returns MCP server results with id, title, and url.

Parameters (2)

querystringrequired
Search query such as healthcare MCP, web search MCP, ChatGPT-compatible MCPs, or OAuth MCP servers.
limitinteger
Maximum number of search results to return.

fetch

ChatGPT-compatible read-only fetch alias. Returns a full MCP server item with id, title, text, url, and metadata.

Parameters (1)

idstringrequired
Canonical MCP server identifier in namespace/name format.

search_servers

Search and rank MCP servers by capability, auth preference, client target, and risk tolerance.

Parameters (6)

capabilitiesarray
Normalized capability taxonomy terms such as healthcare, search, read, exec, files, oauth, or prompts.
auth_preferencestring
Preferred auth mode. Use unauthenticated when the agent must avoid login flows.
client_targetstring
Optional target client or integration surface.
risk_tolerancestring
How much tool-surface risk is acceptable.
querystring
Optional free-text query to bias ranking toward a specific use case or domain.
limitinteger
Maximum number of ranked candidates to return.

recommend_servers

Recommend MCP servers for a plain-language task and return ranked matches with install config.

Parameters (6)

taskstringrequired
Plain-language task description such as 'I need an MCP for healthcare denial scoring in OpenAI connectors'.
capabilitiesarray
Optional explicit capability constraints that override or extend the inferred task capabilities.
auth_preferencestring
Preferred auth mode.
client_targetstring
Optional target client or integration surface.
risk_tolerancestring
How much tool-surface risk is acceptable.
limitinteger
Maximum number of recommendations to return.

get_server_report

Return the full machine-readable verify report for a specific MCP server identifier.

Parameters (1)

identifierstringrequired
Canonical server identifier in namespace/name format.

compare_servers

Compare up to four MCP servers side by side across score, verdict, auth, tool count, prompts/resources, and freshness.

Parameters (1)

identifiersarrayrequired
Canonical server identifiers in namespace/name format.

route_task

Choose the best MCP server/tools for a task. Use decide_agent_call when evaluating one specific attempted tool call.

Parameters (8)

taskstringrequired
Task the agent wants to perform.
candidatestring
Optional namespace/name server identifier to evaluate directly.
capabilitiesarray
Optional capability constraints such as healthcare, search, database, read, or write.
client_targetstring
max_riskstring
Maximum allowed tool risk.
requires_oauthboolean
no_write_without_approvalboolean
max_freshness_hoursnumber

decide_agent_call

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.

Parameters (17)

agent_idstringrequired
user_idstringrequired
server_idstringrequired
Server identifier in namespace/name format.
toolstringrequired
actionstring
mandate_idstring
Optional Verify Mandate key or id.
payload_classificationarray
requested_costnumber
max_costnumber
approval_token_presentboolean
clientstring
max_riskstring
requires_oauthboolean
no_write_without_approvalboolean
max_freshness_hoursnumber
max_runtime_secondsinteger
audit_contextobject

create_mandate

Create a Verify Mandate: signed delegated authority for an agent/user/server scope, budget, validity window, and tool constraints.

Parameters (10)

user_idstringrequired
agent_idstringrequired
server_idstring
scopestringrequired
budget_limitnumber
valid_untilstring
requires_human_approvalboolean
signaturestring
constraintsobject
metadataobject

get_evidence_pack

Return Verify Ledger evidence packs with invocations, hash-chained audit events, decisions, outcomes, mandates, and cost summaries.

Parameters (4)

server_idstring
agent_idstring
user_idstring
limitinteger

compile_docs

Generate agent-readable MCP artifacts from product docs: server card, llms.txt, tool schemas, examples, policy metadata, score preview, and hosted docs page.

Parameters (10)

titlestringrequired
source_typestring
source_urlstring
openapi_specobject
markdown_docsstring
postman_collectionobject
website_docsstring
server_identifierstring
policy_metadataobject
metadataobject

export_policy

Export a JSON TrustOps policy for one MCP server with allow, blocked tools, required scopes, freshness, and approval gates.

Parameters (6)

identifierstringrequired
Canonical server identifier in namespace/name format.
clientstring
max_riskstring
requires_oauthboolean
no_write_without_approvalboolean
max_freshness_hoursnumber

get_subscription_options

Return alert types, subscription channels, watch scopes, and existing subscription endpoints.

No parameters.

get_gateway_options

Return Verify Gateway semantics, /v1/route versus /v1/decide guidance, mandate inputs, ledger evidence hooks, and decision fields.

No parameters.

get_hosting_options

Return Verify Hosted MCP runtime/sandbox hosting capabilities, controls, and endpoints.

No parameters.

list_agents

Agent Sprawl Radar: list discovered AI agents, MCP servers, bots, workflows, risk levels, and owners.

Parameters (2)

risk_levelstring
limitinteger

get_agent

Agent Sprawl Radar: return one agent with tools, data access, findings, drift, and recommended action.

Parameters (1)

agent_idstringrequired

score_agent

Agent Sprawl Radar: score a normalized agent payload or an existing registry agent.

Parameters (2)

agent_idstring
agentobject

explain_agent_risk

Agent Sprawl Radar: explain risk findings and the recommended action for one registry agent.

Parameters (1)

agent_idstringrequired

list_high_risk_agents

Agent Sprawl Radar: list high and critical risk agents for review.

Parameters (1)

limitinteger

get_drift_report

Agent Sprawl Radar: return agent drift events across latest snapshots.

Parameters (2)

agent_idstring
limitinteger

generate_remediation_plan

Agent Sprawl Radar: generate deterministic remediation steps for risky or drifting agents.

Parameters (1)

agent_idstringrequired

Install

claude_desktop_config.json

{
  "mcpServers": {
    "verify": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://verify.sentinelsignal.io/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.