Agentpay Sentinel Mcp
io.github.RumblingbPublished by GitHub account Rumblingbv1.0.0Updated Oct 24, 2026
Security guardrails for AI agent payments
The publisher's own server: AgentPay — Pay-per-call AI Microservices
Overview
A local watchdog MCP that runs pre-flight security checks on AI agent payment requests and returns PASS or BLOCKED verdicts.
- What you can do
- Audit a payment transaction against nine checks (token hash, budget cap, merchant allowlist, blocked categories, expiry, rate limit, amount mismatch, replay, revocation) and get a PASS/BLOCKED verdict with an audit hash
- Revoke a token so future audits block it, and clear a nonce from the replay store for legitimate retries
- Verify that a sequence of audit hashes forms an unbroken chain
- Simulate named attack vectors such as token forgery, budget overflow, replay and merchant spoof, returning severity, defence and detection
- When to use it
- Useful when an agent is allowed to initiate payments and you want a local, advisory gate that checks policy, budget and token integrity before each payment fires. Also handy for reviewing how common payment attack vectors would be detected.
- Requirements
- Runs as a local Python process: Python 3.10+ and the mcp package, launched via a command and script path in the client config (Claude Desktop or Cursor). No API keys or environment variables are declared. State is persisted under the user's home directory.
Installation
In SourceWeft
- Open Agentpay Sentinel Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
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.
Claude Desktop — add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
Cursor — add to .cursor/mcp.json in your project root:
Tool Reference
All 9 checks run by sentinel_audit_transaction
Checks 7–9 activate when the corresponding param is passed. State persists to ~/.sentinel/.
Attack vectors in sentinel_threat_model
token_forgery · budget_overflow · replay_attack · amount_mismatch · revocation_evasion · merchant_spoof · expiry_bypass
Security
sentinel_audit_transaction 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.
Pricing
License
MIT — AgentPay Labs. Source: github.com/Rumblingb/agentpay-sentinel-mcp
Source: README.md at commit eb6284f
Tools
0Version history
1- v1.0.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Agentpay integrations
AgentPay — Pay-per-call AI Microservices
help.agentpayOfficial publisher
AgentPay offers 34 pay-per-call AI and data microservices over x402, settled in USDC on Base, with no API keys required.
AgentPay Doc Tools
Published by GitHub account noah-silver
Remote MCP server offering paid per-call document and web utilities: PDF-to-text, RSS/Atom/JSON feed parsing, and sitemap URL listing.
AgentPay Domain & Network Lookup
Published by GitHub account noah-silver
Remote MCP server for paid DNS, WHOIS/RDAP, IP ownership and combined domain reports, billed per call in USDC or prepaid credits.
AgentPay Web Extract
Published by GitHub account noah-silver
A remote pay-per-call MCP server that fetches a web page and returns clean markdown, metadata and links for an assistant.
AgentPay (all tools)
Published by GitHub account noah-silver
Remote pay-per-call MCP server offering web page extraction, DNS/WHOIS/IP lookups, and PDF, feed and sitemap tools, billed in USDC or prepaid credits.