Agentpay Sentinel MCP server

AgentPay Sentinel MCP

A watchdog MCP that validates every agent payment request against all 9 security checks before it executes — catching policy violations, replay attacks, amount tampering, revoked tokens, and budget overruns at call time.

What your agent can do

• Run a pre-flight audit on any payment transaction before executing it — get PASS or BLOCKED with the specific check that failed
• Validate token integrity: confirms the SHA-256 hash matches the expected merchant_id:amount binding, catching forged or tampered tokens
• Enforce budget caps: rejects transactions where currentspend + amount > budgetcap and returns exact remaining budget
• Check merchant allowlist membership and block purchases in restricted categories
• Verify token expiry and rate limits before the payment fires
• Simulate known attack vectors (token forgery, budget overflow, replay, merchant spoof, expiry bypass) and get the specific defense mechanism and detection method for each

Installation

Requires: Python 3.10+, mcp package.

pip install mcp

Claude Desktop — add to ~/Library/Application Support/Claude/claudedesktopconfig.json (macOS) or %APPDATA%\Claude\claudedesktopconfig.json (Windows):

{
  "mcpServers": {
    "agentpay-sentinel": {
      "command": "python",
      "args": ["/absolute/path/to/agentpay-sentinel-mcp/server.py"]
    }
  }
}

Cursor — add to .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "agentpay-sentinel": {
      "command": "python",
      "args": ["/absolute/path/to/agentpay-sentinel-mcp/server.py"]
    }
  }
}

Tool Reference

All 9 checks run by sentinelaudittransaction

Checks 7–9 activate when the corresponding param is passed. State persists to ~/.sentinel/.

Attack vectors in sentinelthreatmodel

tokenforgery · budgetoverflow · replayattack · amountmismatch · revocationevasion · merchantspoof · expiry_bypass

Security

sentinelaudittransaction returns an advisory verdict — it does not intercept network traffic. Your agent is responsible for calling it before executing a payment and halting on BLOCKED. The audit hash returned is a SHA-256 digest of all check results, giving you a tamper-evident record of each pre-flight decision.

Shortened. The full README is on GitHub.