Before your AI agent pays an unfamiliar endpoint using x402, L402, AP2, MPP, or HTTP 402, this server lets it scan the URL and get back a letter grade (A through F) plus a safety verdict. It exposes two tools: attest_scan for a full report with composite score, danger flags, and pricing, and attest_grade for a quick lookup on previously scanned hosts. The grading logic runs on Attest's servers, so you're installing a thin client that makes HTTPS calls and returns structured JSON. No API key required. Useful if you're building autonomous agents that need a programmatic trust check in their payment loop before authorizing a transaction.
ATTEST_BASE_URLOverride the Attest API base URL. Defaults to https://attestagent.org. Only needed for self-hosting or testing.
Trust scanning for agent payments — right inside your AI agent.
attest-mcp is a Model Context Protocol server that lets any MCP-compatible agent (Claude, Cursor, Windsurf, VS Code, and more) scan an agent payment endpoint and get back a letter grade A–F with a clear safety verdict before authorizing a single cent.
It covers the agentic payment protocols in use today: x402, MPP, AP2, L402, and HTTP 402.
Powered by Attest. The scoring engine runs entirely on Attest's servers — this package is a thin client that relays requests, so installing it never exposes any proprietary grading logic.
Autonomous agents are starting to pay for things on their own. A single malicious or misconfigured endpoint can drain funds through impersonation, a blocklisted payout wallet, bait-and-switch pricing, or a broken payment handshake. attest-mcp gives your agent a fast, deterministic safety check it can run as a step in its payment loop.
| Tool | What it does |
|---|---|
attest_scan | Runs a full scan on a payment endpoint URL and returns a grade (A–F), a composite score (0–100), a verdict, danger flags, price, and a link to the full report. Call this before paying an unfamiliar endpoint. |
attest_grade | Fast lookup of the most recent grade for a host that has already been scanned. Good for a quick pre-check. |
No API key required.
Run it directly with npx (no install needed):
npx attest-mcp
The server speaks MCP over stdio, so you normally don't run it by hand — you point your MCP client at it using one of the configs below.
Edit claude_desktop_config.json (Settings → Developer → Edit Config):
{
"mcpServers": {
"attest": {
"command": "npx",
"args": ["-y", "attest-mcp"]
}
}
}
Add to ~/.cursor/mcp.json (or Settings → MCP → Add new server):
{
"mcpServers": {
"attest": {
"command": "npx",
"args": ["-y", "attest-mcp"]
}
}
}
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"attest": {
"command": "npx",
"args": ["-y", "attest-mcp"]
}
}
}
Add to .vscode/mcp.json in your workspace:
{
"servers": {
"attest": {
"command": "npx",
"args": ["-y", "attest-mcp"]
}
}
}
Use the command npx -y attest-mcp with the stdio transport.
Prefer not to install anything? Attest also runs a hosted MCP server you can connect to over Streamable HTTP:
https://attestagent.org/api/mcp
Point any remote-MCP-capable client at that URL.
Once connected, just ask your agent in natural language:
"Before you pay, scan
https://api.example.com/paid-resourcewith Attest."
The agent calls attest_scan and gets back something like:
{
"host": "api.example.com",
"grade": "A",
"composite": 95,
"danger": false,
"verdict": "Valid endpoint, established host.",
"priceHuman": "0.01 USDC",
"reportUrl": "https://attestagent.org/r/abc-123"
}
| Environment variable | Default | Description |
|---|---|---|
ATTEST_BASE_URL | https://attestagent.org | Override the Attest API base URL. Only needed for self-hosting or testing. |
Issues and pull requests are welcome — see CONTRIBUTING.md.
MIT © Attest
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent
fradser/mcp-server-mas-sequential-thinking