mcpField
P
Paid MCP Metering

Paid MCP Metering

Remote
github.comSearch0Updated 9w ago

About Paid MCP Metering

Paid MCP Metering is an MCP service that offers free tool discovery and charges per execution through x402 v2. Its tools provide live web search and multi-source research; the current deployment has no receiving address configured, so paid execution is unavailable.

Key features

  1. 01Free MCP tool discovery
  2. 02Per-call metered execution
  3. 03Live web search
  4. 04Synthesized research with cited sources
  5. 05x402 v2 USDC settlement

Use cases

  1. 01Discover available search and research tools
  2. 02Add per-call web search to an application
  3. 03Generate multi-source research with citations
  4. 04Configure a receiving address to enable settlement

MCP support

It supports free MCP JSON-RPC initialization and tool discovery, while execution uses a metered HTTP endpoint settled through x402 v2. The live deployment lacks a receiving address, so execution currently returns 503.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://paid-mcp-metering-clsiojdd7-benlafreniere6-3913s-projects.vercel.app/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

paid-mcp-metering

Metered MCP tools, priced per call.

Discovery is free: POST /mcp speaks JSON-RPC 2.0 per the Model Context Protocol (initialize, tools/list, ping). Execution is metered: POST /v1/t/{tool} sits behind an x402 v2 paywall. An unpaid request gets HTTP 402 with payment requirements; a paid request carries a PAYMENT-SIGNATURE header and settles USDC through the facilitator before the tool runs.

Live deployment

Base URL: https://paid-mcp-metering.vercel.app

  • GET /health — free, public
  • POST /mcp — free discovery
  • POST /v1/t/{tool} — metered; currently answers 503 settlement_not_configured because X402_PAY_TO is unset on the deployment (settlementConfigured:false in /health is the honest switch). No payment can be accepted until a receiving address is configured.

server.json declares this URL as the registry remote.

Tools

ToolPriceWhat it returns
web_search$0.001/callRanked live web results with source URLs
deep_research$0.01/callMulti-source research pass with a synthesized answer plus cited sources

Upstreams are Exa (primary) and Tavily (fallback). Every handler returns live upstream output or throws — there is no canned response.

Rails

x402 v2, USDC, EIP-155 network selected by X402_NETWORK (default Base Sepolia testnet, CAIP-2 eip155:84532). Facilitator defaults to https://x402.org/facilitator.

Env varPurpose
X402_PAY_TOReceiving address. Required for settlement; unset serves 402 requirements only
X402_NETWORKCAIP-2 network id (default eip155:84532)
X402_FACILITATOR_URLx402 facilitator endpoint
EXA_API_KEY / TAVILY_API_KEYSearch upstream credentials

Run

npm install
npm run build
npm start          # node dist/x402-server.js
npm test           # build + node --test dist/test-x402.js

Free discovery:

curl -s localhost:4021/mcp -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Paid execution:

curl -s localhost:4021/v1/t/web_search -H 'Content-Type: application/json' \
  -d '{"query":"x402 protocol","max_results":3}'
# -> 402 with payment requirements; pay via an x402 client and retry with PAYMENT-SIGNATURE

Registry

server.json targets the official MCP Registry as io.github.dev55acc-ai/paid-mcp-metering. Tagging v* runs .github/workflows/publish-mcp.yml: tests, build, npm publish (when NPM_TOKEN is set), then registry publish authenticated by GitHub OIDC — no stored registry credential.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.