Server data from the Official MCP Registry
MCP server: x402-paid & free tools for AI agents — provenance, quality scoring, action audit.
MCP server: x402-paid & free tools for AI agents — provenance, quality scoring, action audit.
Valid MCP server (6 strong, 3 medium validity signals). No known CVEs in dependencies. Package registry verified. Imported from the Official MCP Registry.
9 files analyzed · 1 issue found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Set these up before or after installing:
Environment variable: PROVENANCE_URL
Environment variable: QUALITY_GATE_URL
Environment variable: AUDIT_URL
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-gareth1953-agent-services-mcp": {
"env": {
"AUDIT_URL": "your-audit-url-here",
"PROVENANCE_URL": "your-provenance-url-here",
"QUALITY_GATE_URL": "your-quality-gate-url-here"
},
"args": [
"-y",
"agent-services-mcp"
],
"command": "npx"
}
}
}From the project's GitHub README.
A single thin MCP (Model Context Protocol) server that exposes three existing services as discoverable tools, so AI agents and MCP-compatible clients can find and use them through one connection:
It is a thin wrapper. Every tool forwards an HTTP call to the underlying Worker and returns its response verbatim. It does not reimplement signing, scoring, or payment logic — those live in the underlying services. The honesty about what each service proves carries through to the tool descriptions.
npm install && npm run build
node examples/free-call.mjs # connects to the LIVE services and calls a free tool
examples/free-call.mjs runs an MCP client against this server (pointed at the live
deployments) and calls get_quality_rubric and verify_audit — both free, no
wallet needed. To wire the server into an MCP client (Claude Desktop / Claude Code
style), see Connecting an MCP client below.
Free vs paid at a glance: verify_provenance, verify_quality, verify_audit,
and get_quality_rubric are free. certify_provenance, score_quality, and
audit_action are paid (an x402 USDC micropayment on Base) — see Calling paid
tools for the two-step payment flow and a working example.
generator_metadata is caller-attested
— it proves you claimed it, not that a specific model ran. Not AI-detection,
not a truth guarantee.get_quality_rubric tool.action, actor_metadata,
and context are caller-attested — it proves you claimed this record, not
that the agent's claim is true. An accountability/audit tool, not a
lie-detector.| Tool | Forwards to | Paid? | Input |
|---|---|---|---|
certify_provenance | provenance-receipts POST /v1/certify | yes (x402) | content (string), generator_metadata (object, optional) |
verify_provenance | provenance-receipts POST /v1/verify | no | content (string), receipt (object) |
score_quality | quality-gate POST /v1/score | yes (x402) | content (string), rubric_version (string, optional), target_score (number 0–100, optional) |
verify_quality | quality-gate POST /v1/verify | no | content (string), receipt (object) |
get_quality_rubric | quality-gate GET /v1/rubric | no | none |
audit_action | agent-action-audit POST /v1/audit | yes (x402) | action (string), actor_metadata (object), context (object, optional) |
verify_audit | agent-action-audit POST /v1/verify | no | action (string), actor_metadata (object), context (object, optional), receipt (object) |
Full descriptions and Zod input/output schemas: src/tools.ts.
Each tool returns the service's raw JSON (or markdown, for the rubric) as text; the
verify_* and score_quality tools also declare an outputSchema and return
parsed structuredContent you can read directly (e.g. result.structuredContent.valid).
A non-2xx response (including a 402 Payment Required) is surfaced with
isError: true and the body preserved — for a 402 the wrapper prepends a short,
actionable note on how to pay. The three paid tools also accept an optional
x_payment input (the x402 X-PAYMENT token) to settle payment through the
wrapper — see Calling paid tools.
The three service URLs are environment-configurable (no secrets — just base URLs):
| Env var | Live (deployed) | Local dev fallback |
|---|---|---|
PROVENANCE_URL | https://provenance-receipts.gpmiddleton71.workers.dev | http://localhost:8787 |
QUALITY_GATE_URL | https://quality-gate.gpmiddleton71.workers.dev | http://localhost:8788 |
AUDIT_URL | https://agent-action-audit.gpmiddleton71.workers.dev | http://localhost:8789 |
.env.example and the client config below point at the live deployments. If
the vars are unset, the server falls back to localhost for local wrangler dev
(the Workers default to :8787, so run quality-gate on :8788 and
agent-action-audit on :8789 to avoid clashes).
Against the live services, the paid tools (
certify_provenance,score_quality,audit_action) require x402 — this wrapper forwards the request and holds no wallet, so without anX-PAYMENTthey return a402(the payment requirements) surfaced asisError. The free tools work as normal.
The three paid tools require an x402 micropayment (USDC on Base mainnet). The wrapper holds no wallet — it never spends on your behalf — so paying is a two-step flow:
x_payment. You get back a 402 whose body is the x402
payment requirements (network, asset, amount, payTo). The wrapper prepends a
one-line note explaining what to do next.X-PAYMENT token from those requirements with an x402 client +
a funded wallet, then call the tool again with that token in the x_payment
input. The wrapper forwards it as the X-PAYMENT header; the underlying service
verifies, settles, and returns the signed receipt.Easiest path to a working paid call — let an x402 client settle for you against the underlying service directly:
npm install x402-fetch
BUYER_PRIVATE_KEY=0x... node examples/paid-call.mjs
examples/paid-call.mjs uses x402-fetch + a throwaway Base-mainnet wallet
(holding a little real USDC) to pay for and call audit_action. ~$0.01 USDC moves
buyer → the service's payTo, gasless (the facilitator pays gas). Real money — use
a disposable key with a few cents only. The same applies to certify_provenance
and score_quality.
# 1. Build the MCP server
npm install
npm run build # -> dist/index.js
# 2. In separate terminals, run the three services (free; payments off)
# (provenance-receipts) npm run dev # http://localhost:8787
# (quality-gate) npx wrangler dev --port 8788 # http://localhost:8788
# (agent-action-audit) npx wrangler dev --port 8789 # http://localhost:8789
# 3a. Smoke-test the free tool paths through an MCP stdio client
node scripts/test-client.mjs
# 3b. (optional, costs ~$0.012) prove the paid score_quality path end-to-end
node scripts/test-score.mjs
# 3c. Smoke-test the wrapper against the LIVE deployed services (free — the
# paid tools return a forwarded 402; no payment, no scoring call)
node scripts/test-live.mjs
scripts/test-client.mjs exercises the free tools locally; scripts/test-score.mjs
makes one real Anthropic scoring call through score_quality;
scripts/test-live.mjs points the wrapper at the deployed workers.dev URLs and
asserts the free tools work and the paid tools forward the x402 402.
This server speaks MCP over stdio (stdin/stdout). Any MCP client launches it
as a subprocess. Example for a Claude Desktop / Claude Code style
mcpServers config:
{
"mcpServers": {
"agent-services": {
"command": "node",
"args": ["C:\\Users\\Gareth\\agent-services-mcp\\dist\\index.js"],
"env": {
"PROVENANCE_URL": "https://provenance-receipts.gpmiddleton71.workers.dev",
"QUALITY_GATE_URL": "https://quality-gate.gpmiddleton71.workers.dev",
"AUDIT_URL": "https://agent-action-audit.gpmiddleton71.workers.dev"
}
}
}
}
npm run build first so dist/index.js exists.tools/list (it will see the 7 tools above), and
invokes them via tools/call.Programmatically, connect with the SDK's Client + StdioClientTransport
(command: "node", args: ["dist/index.js"]) — see scripts/test-client.mjs.
The paid endpoints (/v1/certify, /v1/score, /v1/audit) are gated by
x402 on the underlying services. This wrapper
forwards requests and does not hold a wallet. If a service has payments
enabled and no valid X-PAYMENT is supplied, it returns 402 with the payment
requirements — the wrapper surfaces that as isError with the requirements body
intact. Settling a payment (signing an x402 authorization) is the client's
responsibility against the underlying service. See each service's README.md /
docs/API.md for the x402 details. Base Sepolia testnet only — no mainnet.
The receipts returned by certify_provenance, score_quality, and audit_action
are Ed25519-signed and verifiable without trusting any of these services —
re-hash the content/record and check the signature against the service's public
key. Each service ships a runnable independent verifier and recipe: see
provenance-receipts/docs/VERIFYING.md,
quality-gate/docs/VERIFYING.md,
and agent-action-audit's docs/VERIFYING.md.
src/tools.ts)*.gpmiddleton71.workers.dev)
and verified end-to-end via scripts/test-live.mjs: free tools work; paid
tools forward the x402 402.All seven tool paths verified against the live deployments (including one paid
score_quality call end-to-end through the wrapper); the paid tools
(certify_provenance, score_quality, audit_action) forward the x402 402.
@modelcontextprotocol/sdk
v1.29.0 (TypeScript), stdio transport, zod
input schemas.tsc → dist/).agent-services-mcp/
├── src/
│ ├── index.ts # MCP server: registers tools, forwards HTTP, stdio transport
│ └── tools.ts # the 7 tool definitions (names, descriptions, Zod schemas)
├── scripts/
│ ├── test-client.mjs # MCP stdio client — free tool smoke test (local)
│ ├── test-score.mjs # MCP stdio client — one paid score_quality e2e check
│ └── test-live.mjs # MCP stdio client — against the live deployed services
├── package.json
├── tsconfig.json
├── .gitignore
└── .env.example # PROVENANCE_URL, QUALITY_GATE_URL, AUDIT_URL
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.