Official MCP RegistryListed
MCP Verify
Trust, freshness, policy, and discovery layer for public MCP servers.
First seen 2 Oct 2026. Evidence as of 7 Oct 2026.
22
Tools
From an anonymous probe
1
Source listings
Each with its own history
0
Recorded changes
Since first seen
Tools
| Tool | Description | Behaviour |
|---|---|---|
| compare_servers | Compare up to four MCP servers side by side across score, verdict, auth, tool count, prompts/resources, and freshness. | Read-only |
| 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. | Changes data |
| create_mandate | Create a Verify Mandate: signed delegated authority for an agent/user/server scope, budget, validity window, and tool constraints. | Changes data |
| 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. | Changes data |
| explain_agent_risk | Agent Sprawl Radar: explain risk findings and the recommended action for one registry agent. | Read-only |
| export_policy | Export a JSON TrustOps policy for one MCP server with allow, blocked tools, required scopes, freshness, and approval gates. | Read-only |
| fetch | ChatGPT-compatible read-only fetch alias. Returns a full MCP server item with id, title, text, url, and metadata. | Read-only |
| generate_remediation_plan | Agent Sprawl Radar: generate deterministic remediation steps for risky or drifting agents. | Read-only |
| get_agent | Agent Sprawl Radar: return one agent with tools, data access, findings, drift, and recommended action. | Read-only |
| get_drift_report | Agent Sprawl Radar: return agent drift events across latest snapshots. | Read-only |
| get_evidence_pack | Return Verify Ledger evidence packs with invocations, hash-chained audit events, decisions, outcomes, mandates, and cost summaries. | Read-only |
| get_gateway_options | Return Verify Gateway semantics, /v1/route versus /v1/decide guidance, mandate inputs, ledger evidence hooks, and decision fields. | Read-only |
| get_hosting_options | Return Verify Hosted MCP runtime/sandbox hosting capabilities, controls, and endpoints. | Read-only |
| get_server_report | Return the full machine-readable verify report for a specific MCP server identifier. | Read-only |
| get_subscription_options | Return alert types, subscription channels, watch scopes, and existing subscription endpoints. | Read-only |
| list_agents | Agent Sprawl Radar: list discovered AI agents, MCP servers, bots, workflows, risk levels, and owners. | Read-only |
| list_high_risk_agents | Agent Sprawl Radar: list high and critical risk agents for review. | Read-only |
| recommend_servers | Recommend MCP servers for a plain-language task and return ranked matches with install config. | Read-only |
| route_task | Choose the best MCP server/tools for a task. Use decide_agent_call when evaluating one specific attempted tool call. | Read-only |
| score_agent | Agent Sprawl Radar: score a normalized agent payload or an existing registry agent. | Read-only |
| search | ChatGPT-compatible read-only search alias. Returns MCP server results with id, title, and url. | Read-only |
| search_servers | Search and rank MCP servers by capability, auth preference, client target, and risk tolerance. | Read-only |
Change history
No changes since the first observation. The first snapshot is the baseline.
| Source | Listing | First seen | Last seen | Versions |
|---|---|---|---|---|
| Official MCP Registry | io.sentinelsignal/verify | 2 Oct 2026 | 7 Oct 2026 | 1 |