mcp server
MCP Verify
Trust, freshness, policy, and discovery layer for public MCP servers.
Description as published by the maintainer. Source
- version 1.0.269
- active
active — Registry entry last updated 2026-05-24.
What this server can do
22 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
compare_servers(identifiers)- Compare up to four MCP servers side by side across score, verdict, auth, tool count, prompts/resources, and freshness. Required: identifiers.
compile_docs(title, metadata, source_url, source_type, openapi_spec, website_docs, markdown_docs, policy_metadata, server_identifier, postman_collection)- Generate agent-readable MCP artifacts from product docs: server card, llms.txt, tool schemas, examples, policy metadata, score preview, and hosted docs page. Required: title.
create_mandate(scope, user_id, agent_id, metadata, server_id, signature, constraints, valid_until, budget_limit, requires_human_approval)- Create a Verify Mandate: signed delegated authority for an agent/user/server scope, budget, validity window, and tool constraints. Required: user_id, agent_id, scope.
decide_agent_call(tool, action, client, user_id, agent_id, max_cost, max_risk, server_id, mandate_id, audit_context, requested_cost, requires_oauth, max_freshness_hours, max_runtime_seconds, approval_token_present, payload_classification, no_write_without_approval)- 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. Required: agent_id, user_id, server_id, tool.
explain_agent_risk(agent_id)- Agent Sprawl Radar: explain risk findings and the recommended action for one registry agent. Required: agent_id.
export_policy(client, max_risk, identifier, requires_oauth, max_freshness_hours, no_write_without_approval)- Export a JSON TrustOps policy for one MCP server with allow, blocked tools, required scopes, freshness, and approval gates. Required: identifier.
fetch(id)- ChatGPT-compatible read-only fetch alias. Returns a full MCP server item with id, title, text, url, and metadata. Required: id.
generate_remediation_plan(agent_id)- Agent Sprawl Radar: generate deterministic remediation steps for risky or drifting agents. Required: agent_id.
get_agent(agent_id)- Agent Sprawl Radar: return one agent with tools, data access, findings, drift, and recommended action. Required: agent_id.
get_drift_report(limit, agent_id)- Agent Sprawl Radar: return agent drift events across latest snapshots.
get_evidence_pack(limit, user_id, agent_id, server_id)- Return Verify Ledger evidence packs with invocations, hash-chained audit events, decisions, outcomes, mandates, and cost summaries.
get_gateway_options- Return Verify Gateway semantics, /v1/route versus /v1/decide guidance, mandate inputs, ledger evidence hooks, and decision fields.
get_hosting_options- Return Verify Hosted MCP runtime/sandbox hosting capabilities, controls, and endpoints.
get_server_report(identifier)- Return the full machine-readable verify report for a specific MCP server identifier. Required: identifier.
get_subscription_options- Return alert types, subscription channels, watch scopes, and existing subscription endpoints.
list_agents(limit, risk_level)- Agent Sprawl Radar: list discovered AI agents, MCP servers, bots, workflows, risk levels, and owners.
list_high_risk_agents(limit)- Agent Sprawl Radar: list high and critical risk agents for review.
recommend_servers(task, limit, capabilities, client_target, risk_tolerance, auth_preference)- Recommend MCP servers for a plain-language task and return ranked matches with install config. Required: task.
route_task(task, max_risk, candidate, capabilities, client_target, requires_oauth, max_freshness_hours, no_write_without_approval)- Choose the best MCP server/tools for a task. Use decide_agent_call when evaluating one specific attempted tool call. Required: task.
score_agent(agent, agent_id)- Agent Sprawl Radar: score a normalized agent payload or an existing registry agent.
search(limit, query)- ChatGPT-compatible read-only search alias. Returns MCP server results with id, title, and url. Required: query.
search_servers(limit, query, capabilities, client_target, risk_tolerance, auth_preference)- Search and rank MCP servers by capability, auth preference, client target, and risk tolerance.
Last successful function declaration observed on . Source: https://verify.sentinelsignal.io/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://verify.sentinelsignal.io/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| Latest published version | 1.0.269 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-05-24 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| First listed in the MCP Registry | 2026-05-24 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| mcp tools declared | 22 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | verify.sentinelsignal.io | |
| mcp endpoint status | ok | The server listed 22 functions when asked. | as of probe | verify.sentinelsignal.io |
Where to get it
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json