Agentpay Sentinel Mcp
A pre-flight security layer for AI agents that handle payments. Exposes five tools, led by sentinel_audit_transaction, which runs nine checks on every payment request: token integrity via SHA-256, budget caps, merchant allowlists, category blocks, expiry, rate limits, amount tampering, replay attacks, and token revocation. The audit returns PASS or BLOCKED with the specific failing check. State persists to disk so nonces and revoked tokens survive restarts. Also includes sentinel_threat_model for simulating known attack vectors like token forgery and budget overflow. Reach for this when your agent needs to execute payments but you want a cryptographic audit trail and defense against common evasion tactics before any money moves.
- GitHub stars
- 1
- tools
- 5
- last updated
- Jun 3, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
sentinel_audit_transactionRun all 9 security checks; returns PASS/BLOCKED + SHA-256 audit hash
Run all 9 security checks; returns PASS/BLOCKED + SHA-256 audit hash
No parameter schema in public metadata yet.
sentinel_revoke_tokenPermanently revoke a token — all future audits with this token_id will BLOCK
Permanently revoke a token — all future audits with this token_id will BLOCK
No parameter schema in public metadata yet.
sentinel_clear_nonceRemove a nonce from the replay store (for legitimate refunds/retries only)
Remove a nonce from the replay store (for legitimate refunds/retries only)
No parameter schema in public metadata yet.
sentinel_verify_chainVerify a sequence of audit hashes forms an unbroken chain
Verify a sequence of audit hashes forms an unbroken chain
No parameter schema in public metadata yet.
sentinel_threat_modelSimulate any named attack vector; returns severity, defence, and detection
Simulate any named attack vector; returns severity, defence, and detection
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
AgentPay
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:amountbinding, catching forged or tampered tokens - Enforce budget caps: rejects transactions where
current_spend + amount > budget_capand 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
Details
- Repository
- github.com/rumblingb/agentpay-sentinel-mcp
- Categories
- AI & LLM Tools, Security & Pentesting
- Registry
- MCP registry, active
More from rumblingb
Related AI & LLM Tools MCP servers
View all
Forge Cascade MCP Memory Serversunflash12/forge-cascade-mcpAI memory buyer routing with Forge docs, pricing, paid recommendations, and MCP discovery.1stars
Mcp Serverthe402ai/mcp-serverAI agent service marketplace — browse, purchase, and manage services via x402/USDC0stars
Skill Deckxingbofeng/skill-deckExpose local Agent Skills as adapter tools, MCP resources, MCP tools, and share artifacts.1stars
BIP Skills MCP2fizzle/bip-skills-mcpServes Agent Skills folders (SKILL.md + bundled files) to any MCP client. Bundles bip-xsl-hardening.0stars
Myagi - Open Agent Registryaaronkpickrell/openagent-registryScore any website's AI-agent readiness. Open Agent Registry scanner + platform tools.0stars
Agentforgeacarchidi/agentforgeSafety checks for AI agents: preflight before signing, prompt-injection scan, sanctions, rug checks.0stars