mcpField
X
X402 Payment Gated Http

X402 Payment Gated Http

Local
github.com/merkleworksFinance0Updated 33w ago

About X402 Payment Gated Http

X402 Payment Gated Http is an MCP server for AI agents calling HTTP APIs that charge per request. It can discover payable endpoints and handle x402 payment, request retry, and response retrieval when an API returns 402.

Key features

  1. 01Call payment-gated HTTP APIs
  2. 02Handle 402 challenges, payment, and retries
  3. 03Discover payable API endpoints
  4. 04Parse challenges and verify payment proofs
  5. 05Control request method, body, and headers

Use cases

  1. 01Let an agent access APIs charged per request
  2. 02Find x402 endpoints exposed by a service
  3. 03Handle a 402 payment flow during an API call
  4. 04Inspect x402 challenges and payment proofs

MCP support

The MCP server exposes HTTP request, endpoint discovery, payment, and challenge verification tools to agents. When an API returns 402, it can pay through the x402 flow and retry with proof.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"x402": {
"command": "npx",
"args": [
"-y",
"@merkleworks/x402-mcp"
]
}
}
}
Run commandnpx -y @merkleworks/x402-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@merkleworks/x402-mcp

Tools

4

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
urlstringYesBase URL or specific endpoint URL to discover x402 APIs on

Details

From the project README

x402-mcp

MCP server for the x402 protocol. Lets AI agents (Claude, Cursor, etc.) discover and call payment-gated HTTP APIs automatically.

Repository: merkleworks/x402-mcp


MCP Server

This repository provides a Model Context Protocol (MCP) server that enables AI agents to call payment-gated HTTP APIs using the x402 protocol.

Tools exposed:

  • x402_http_request — Execute HTTP requests to APIs requiring payment via the x402 protocol. If the server returns 402, the tool parses the challenge, constructs the payment, retries with proof, and returns the final response.

Example agent flow:

agent → tool call → x402_http_request → 402 challenge → payment → retry → response

Automatic discovery: The server is discoverable by MCP-aware frameworks without manual registry submission:

  • Repository descriptor: mcp.json at the repo root (name, description, install: npx x402-mcp, tools).
  • npm: Run with npx x402-mcp; package keywords include mcp, model-context-protocol, ai-tools, x402.
  • Well-known: .well-known/mcp.json can be hosted at https://demo.x402.merkleworks.io/.well-known/mcp.json for domain-based discovery.

Overview of x402

x402 is a protocol that gates HTTP APIs behind micropayments using HTTP 402 Payment Required:

  1. Request — Client calls the API.
  2. 402 challenge — Server responds with 402 Payment Required and an X402-Challenge header (nonce UTXO, price, payee, expiry).
  3. Payment — Client builds a BSV transaction, delegates fees (optional), and broadcasts.
  4. Retry — Client retries the request with an X402-Proof header.
  5. Response — Server verifies the proof and returns the API response.

This flow lets APIs charge per request in satoshis without pre-registration or cards.


What this MCP server does

This server exposes Model Context Protocol (MCP) tools so AI agents can:

  • paid_http_request — Send an HTTP request; if the server returns 402, run the full x402 flow (parse challenge → pay → retry with proof) and return the final response. Primary tool for calling payment-gated APIs.
  • discover_x402_api — List payable endpoints (from /.well-known/x402 or by probing for 402).
  • pay_x402_endpoint — Call a known x402 endpoint with full control (method, body, headers, delegator).
  • parse_x402_challenge — Decode an X402-Challenge header.
  • verify_x402_proof — Check an X402-Proof against a challenge and request.

Agents use paid_http_request for a single “call this URL; pay if 402” step.


Installation

Run with a single command (recommended):

npx x402-mcp

Or install globally:

npm install -g x402-mcp
x402-mcp

From source:

git clone https://github.com/merkleworks/x402-mcp.git
cd x402-mcp
npm install
npm run build
npm start

Usage example

Agent → tool call → x402_http_request → x402 flow (if 402) → API response

  1. The agent calls the tool with url, method, and optional headers and body.
  2. The server sends the HTTP request.
  3. If the response is 402, the server parses the challenge, builds the payment, delegates/broadcasts, then retries with the proof.
  4. The tool returns the final response (status, body, and payment txid if paid).

Example tool call

Tool: x402_http_request

Input schema:

FieldTypeRequiredDescription
urlstringyesFull URL of the API endpoint
methodstringnoHTTP method (default: GET)
headersobjectnoOptional HTTP headers (key-value strings)
bodystring or objectnoOptional request body (string or JSON object)

Example (GET):

{
  "tool": "x402_http_request",
  "input": {
    "url": "https://demo.x402.merkleworks.io/v1/expensive",
    "method": "GET"
  }
}

Example (POST with JSON body):

{
  "tool": "x402_http_request",
  "input": {
    "url": "https://api.example.com/v1/query",
    "method": "POST",
    "headers": { "Content-Type": "application/json" },
    "body": { "query": "example" }
  }
}

More examples: examples/, including example_agent_call.json.


Connecting from AI clients

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "x402": {
      "command": "npx",
      "args": ["@merkleworks/x402-mcp"]
    }
  }
}

Or with a local build:

{
  "mcpServers": {
    "x402": {
      "command": "node",
      "args": ["/path/to/x402-mcp/dist/server.js"]
    }
  }
}
Claude Desktop / Claude Code

Add to your MCP config (e.g. claude_desktop_config.json):

{
  "mcpServers": {
    "x402": {
      "command": "npx",
      "args": ["@merkleworks/x402-mcp"]
    }
  }
}
Generic MCP client (Node.js)
import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";

const transport = new StdioClientTransport({
  command: "npx",
  args: ["@merkleworks/x402-mcp"],
});

const client = new Client({ name: "my-agent", version: "1.0.0" });
await client.connect(transport);

const result = await client.callTool("paid_http_request", {
  url: "https://demo.x402.merkleworks.io/v1/expensive",
  method: "GET",
});
console.log(result);

Tools reference

ToolDescription
paid_http_requestExecute HTTP request; if 402, run x402 flow and return final response
discover_x402_apiDiscover payable endpoints (/.well-known/x402 or probe)
pay_x402_endpointCall x402 endpoint with full control (delegator, broadcast URL, etc.)
parse_x402_challengeDecode X402-Challenge header
verify_x402_proofVerify X402-Proof against challenge and request

Protocol summary

  1. Client requests a protected endpoint.
  2. Server responds 402 with X402-Challenge.
  3. Client builds a BSV tx, optionally uses a delegator for fees, then broadcasts.
  4. Client retries with X402-Proof.
  5. Server verifies and returns the response.

This MCP server implements that flow so agents can pay for API calls without manual steps.


Configuration

  • pay_x402_endpoint (and thus paid_http_request when it pays) use the same origin as the request URL for the delegator by default. Override with delegator_url / broadcast_url when using pay_x402_endpoint directly.
  • Discovery manifest format: protocol spec and /.well-known/x402.

Examples

  • example_agent_call.json — Example paid_http_request call for agents.
  • discover-and-pay — Discover endpoints then pay and call the first. Run: npx tsx examples/discover-and-pay.ts https://your-x402-api.example.com

MCP registry (mcp.json)

The repo includes mcp.json for MCP registries (e.g. mcp.so): name, description, repository, install command, and tool list.


License

Apache-2.0

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.