Agency Check
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
Agency Check
A hosted MCP server that checks what your AI agent is about to do before it acts.
A second look before your AI agent buys, sends, books, shares, signs up, or connects an app.
Website: https://agency-check.app
MCP endpoint (Streamable HTTP):
https://agency-check.app/mcpOfficial MCP Registry:
io.github.CyberStrategy1/agency-check— https://registry.modelcontextprotocol.io/v0/servers?search=agency-check
This repository holds documentation only. Agency Check is a hosted service; there is nothing to install or self-host.
Tools
Tool | What it does |
| Check a planned agent action before it runs (counts as one check). |
| Describe the ruleset Agency Check uses (free). |
| Explain a single rule by its ID, e.g. |
| Fetch a signed receipt for a past check by receipt ID (free). |
Related MCP server: @costrinity/vitna-compliance-mcp
Connect
Sign-in is OAuth (Google). Your MCP client opens a browser window the first time it connects. See docs/connect.md for Claude, Cursor, ChatGPT, VS Code, and generic clients.
Quick Cursor mcp.json:
{
"mcpServers": {
"agency-check": { "url": "https://agency-check.app/mcp" }
}
}Pricing
Free: 20 checks a month, no card. Sign in with Google.
Agency Check Pro: $9/month or $79/year. Upgrade from https://agency-check.app/account.
Only
agency_checkcalls count;describe_ruleset,explain_rule,get_receipt, and follow-ups answering a Clarify question are free. Allowances reset on the 1st of each month (UTC).Details: https://agency-check.app/pricing
Links
Privacy: https://agency-check.app/privacy
Support: https://agency-check.app/support
Made by Cyber Strategy Institute. Docs licensed CC BY 4.0.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Authorize AI agent tool calls before they run: policy-as-code, human approval, signed receipts.
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
Checks AI agent actions before they run. Signed, RFC 3161 timestamped evidence for audits.
Check, limit, record and prove AI agent actions with 2-of-3 validators and onchain proofs.
Related MCP Servers
AlicenseNot gradedqualityBmaintenanceEnables AI agents to query live, human-approved rules before taking actions, ensuring compliance and reducing errors.30Apache 2.0- AlicenseAqualityBmaintenanceA containment layer for AI agents that go rogue. Guard mode wraps stdio MCP servers: calls to the tools you mark as risky wait for a person; if nobody decides in time, the call is blocked. No API key can decide a hold, including the agent’s own. Claimed accounts get Ed25519-signed session records you verify offline. Covers only the servers you wrap; detection is heuristic. Free tier, MIT client.2375 npmMIT
- AlicenseNot gradedqualityCmaintenanceProvides tools to evaluate an AI agent's step before execution, returning signed ALLOW/DENY receipts, and to verify receipt chain integrity.Apache 2.0
- AlicenseAqualityBmaintenanceOwner-signed authorization before agent actions. Hosted Vizier v0.5.13 MCP: https://vizier.agendamcp.dpdns.org/mcp. ALLOW/BLOCK/REVIEW; anonymous calls never ALLOW. Your integration enforces the decision. SDK v0.5.13: https://www.npmjs.com/package/@agenda-intelligence/vizier-sdk. Grants are signed; legacy receipts are unsigned. Python stdio is a separate catalog.3MIT