zekebuilds-lab/captcha-mcp

🔒 Security
0 Views
0 Installs

📇 🏠 🍎 🪟 🐧 - L402 Lightning paywall + Hashcash proof-of-work gate for MCP tool calls. Free tier solves a PoW challenge; paid tier pays a Lightning invoice via self-hosted LNBits. No accounts, no API keys, no third-party SaaS. Drop-in middleware for any MCP server. npx @powforge/captcha-mcp.

Quick Install

One-Click IDE Configuration
claude_desktop_config.json
{
  "mcpServers": {
    "zekebuilds-lab-captcha-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "zekebuilds-lab-captcha-mcp"
      ]
    }
  }
}
Or

Using an AI coding agent (Claude Code, Cursor, etc.)? Copy a ready-made prompt that tells it to fetch the setup instructions and install this server for you.

Documentation Overview

@powforge/captcha-mcp

Charge AI agents per-call without accounts. PoW solve = free tier. Lightning payment = paid tier.

OpenAI's Sora API does not let you charge per call. Anthropic's billing does not pass through to your tools. If you ship an MCP server today and an autonomous agent finds it, you eat the bill.

This is the gate. Three tools over stdio or HTTP. Stdlib only.

Quickstart

npx -y @powforge/captcha-mcp

That is it. No install, no config, no API key. The server starts on stdio and waits for an MCP client.

To wire it into Claude Code, Cursor, or any MCP-compatible host, add to your config:

{
  "mcpServers": {
    "powforge-captcha": {
      "command": "npx",
      "args": ["-y", "@powforge/captcha-mcp"]
    }
  }
}

Or run npx @powforge/captcha-mcp --install to print the config block.

What it does

Wraps the PowForge pow-captcha service (captcha.powforge.dev) as three MCP tools:

ToolPurpose
challengeRequest a fresh proof-of-work puzzle. Returns {id, salt, difficulty, signature}.
verifySubmit a solved nonce. Returns a 5-minute HMAC-signed access token.
statusServer health, lifetime stats, L402 endpoint metadata.

The free tier costs the agent ~5-10 seconds of CPU time (SHA-256, default 14 leading zero bits). The paid tier costs 3 sats over Lightning via L402 (RFC 7235 + bolt11 invoice in WWW-Authenticate).

Why this and not OAuth, API keys, or Stripe

ApproachPer-call costAccount requiredSelf-hostedAgent-friendly
API keys$0yesn/ano
OAuth$0yesn/ano
Stripe meteringhigh overheadyesn/ano
Managed MCP auth platform100–2000 satsnonoyes
PoW + L402 (this)seconds or 3 satsnoyesyes

Agents do not have email addresses. They do not click confirmation links. They do not enter credit cards. PoW + Lightning is the only auth primitive that works for fully autonomous callers.

Managed MCP auth platforms work, but they charge 100–2000 sats per call on vendor infrastructure — your revenue flows through their rails. This package runs on your server, your Lightning node, your keys. You keep the sats.

Configuration

Set CAPTCHA_URL to point at a different captcha backend. Default is http://localhost:3077 so you can run the full stack locally for development. Production deployments point it at https://captcha.powforge.dev.

CAPTCHA_URL=https://captcha.powforge.dev npx @powforge/captcha-mcp

HTTP Streamable transport

Hosted MCP clients (Smithery, browser-based hosts) need HTTP, not stdio. Pass --http or set HTTP_MODE=1:

HTTP_MODE=1 PORT=3200 npx @powforge/captcha-mcp
# or
npx @powforge/captcha-mcp --http

The server then listens on:

EndpointMethodPurpose
/mcpPOSTSingle JSON-RPC request, single JSON-RPC response. Notifications return 202.
/mcpGETSSE stream for server-pushed notifications (kept open with a 25s heartbeat).
/healthGETLiveness probe — returns {ok, server, transport}. Not part of MCP.

Stateless. No session ids. CORS open (Access-Control-Allow-Origin: *) so browser clients work. Stdio mode is unchanged and remains the default — npx @powforge/captcha-mcp with no flag still talks JSON-RPC over stdin/stdout.

Smoke test the HTTP transport:

HTTP_MODE=1 PORT=3200 node src/server.js &
curl -X POST http://localhost:3200/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1"}}}'

Returns {jsonrpc:"2.0", id:1, result:{protocolVersion:"2024-11-05", capabilities:{tools:{}}, serverInfo:{...}}}.

Local development

Clone the captcha widget repo or run the public service. The MCP server only needs HTTP access to the captcha endpoints listed under status.

git clone https://github.com/zekebuilds-lab/captcha-mcp
cd captcha-mcp
node src/server.js

It prints ready to stderr and waits for JSON-RPC on stdin.

Smoke-test the protocol manually:

echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1"}}}' | node src/server.js

You should see a JSON response with serverInfo: { name: "@powforge/captcha-mcp", version: "0.1.0" }.

Token verification from your own backend

When an agent submits a token to your service, verify it without trusting the agent:

curl -X POST https://captcha.powforge.dev/api/token/verify \
  -H "Content-Type: application/json" \
  -d '{"token":"<token-from-verify-tool>"}'

Returns {valid: true, method, issued_at, expires_at} or {valid: false, reason}.

Related packages

How this compares to other MCP agent-auth primitives

A side-by-side breakdown against x402-mcp, @agentauth/mcp, and Cloudflare ARC/ACT is published at powforge.dev/mcp/compare/x402-mcp. Short version: captcha-mcp is the only entrant that ships a free PoW tier alongside a Lightning paid skip on an MCP transport. The other three price every call (USDC) or require platform-issued credentials.

License

MIT

Related MCP Servers

13bm/GhidraMCP

🐍 ☕ 🏠 - MCP server for integrating Ghidra with AI assistants. This plugin enables binary analysis, providing tools for function inspection, decompilation, memory exploration, and import/export analysis via the Model Context Protocol.

🔒 Security1 views
123Ergo/unphurl-mcp

📇 ☁️ - URL intelligence for AI agents. 13 tools for security signals and data quality: redirect behaviour, brand impersonation detection, domain age, SSL validation, parked detection, URL structural analysis, DNS enrichment.

🔒 Security0 views
82ch/MCP-Dandan

🐍 📇 🏠 🍎 🪟 🐧 - Real-time security framework for MCP servers that detects and blocks malicious AI agent behavior by analyzing tool call patterns and intent across multiple threat detection engines.

🔒 Security0 views
9hannahnine-jpg/arc-gate-mcp

🐍 - Runtime governance for MCP tool calls. Blocks prompt injection and capability abuse before tool results reach your agent.

🔒 Security0 views

Engagement

Views
0
Installs
0
Upvotes
0

Views and upvotes are unique per visitor network (hashed IP). Installs count copy actions.

Status

Health: Not checked yet

We have not completed a health check for this listing yet.

No check timestamp yet.

Unclaimed listing (imported or pending owner verification). Claim it →
★ Spotlight Slot

Feature Your MCP Server

Get maximum visibility for your server across our directory, search results, and detail pages.

Spotlight Your Server

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to get the verified badge and attach your website.

Claim this listing

Promote this listing

Optional paid placement. Free listings stay free forever.

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.