Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Search 20k+ live, probed x402 pay-per-call endpoints and route to the best-scored one.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"x402-router": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/camerxnduff/x402-router-mcp:0.1.0"
]
}
}
}Run this in your terminal
claude mcp add x402-router -- docker run -i --rm ghcr.io/camerxnduff/x402-router-mcp:0.1.0Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"x402-router": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/camerxnduff/x402-router-mcp:0.1.0"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"x402-router": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/camerxnduff/x402-router-mcp:0.1.0"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026
The registry name was verified with the GitHub account camerxnduff, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.0) reached the registry 14 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Docker on your computer.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
20,700+ LIVE x402 pay-per-call endpoints across 3,100+ services, probed every 3 hours and scored 0-100 for reliability. Agents don't need to know which x402 API is up. Ask the router.
Keywords: x402, MCP, MCP server, AI agents, agent payments, pay-per-call APIs, USDC, Base, Solana, x402 discovery, x402 router, x402 registry, HTTP 402.
The server is read-only: it holds no keys and never pays. It exposes four tools: search_x402_endpoints, route_x402_request, get_registry_stats, get_paid_route_requirements.
Claude Desktop (claude_desktop_config.json) or Cursor (~/.cursor/mcp.json):
{
"mcpServers": { "x402-router": { "command": "uvx", "args": ["--from", "git+https://github.com/camerxnduff/x402-router-mcp#subdirectory=mcp-server", "x402-router-mcp"] } } }
{
"mcpServers": { "x402-router": { "command": "docker", "args": ["run", "-i", "--rm", "ghcr.io/camerxnduff/x402-router-mcp:latest"] } } }
Or build it yourself: `docker build -t x402-router-mcp .` and use `x402-router-mcp` as the image name.
git clone https://github.com/camerxnduff/x402-router-mcp
cd x402-router-mcp/mcp-server python3 -m venv .venv && . .venv/bin/activate pip install -r requirements.txt python test_client.py # calls the live router, read-only
```json
{"mcpServers":{"x402-router":{"command":"/abs/path/x402-router-mcp/mcp-server/.venv/bin/python","args":["/abs/path/x402-router-mcp/mcp-server/server.py"]}}}
Streamable HTTP: `python server.py --http 8000` serves `http://localhost:8000/mcp`.
Env overrides: X402_ROUTER_URL, X402_DASHBOARD_URL.
# best live Base endpoint for a category (free preview)
curl -s -X POST https://router-production-ab89.up.railway.app/route \ -H 'content-type: application/json' -d '{"category":"Finance","chain":"Base"}'
curl -s 'https://router-production-ab89.up.railway.app/dashboardapi/endpoints?q=weather&chain=Base&limit=5'
Thousands of x402 endpoints exist, and many are dead, misconfigured or slow. The router probes every one, checks that its 402 body is valid (version, scheme, network, payTo, asset, amount), and ranks by uptime and latency, so an agent gets a working endpoint with a known price.
| Endpoint | What |
|---|---|
GET /api/endpoints?q=&chain=&category=&max_price=&min_score=&sort=&limit= (dashboard) | Search LIVE endpoints, best first |
GET /api/summary (dashboard) | Counts by chain, category, source |
GET /api/registry (dashboard) | Full registry (gzip) |
POST /route (router) | Best match + top 3, free |
POST /route/paid (router) | $0.01 USDC (x402, Base; Solana accepted): full ranked list (up to 25) with latency, reliability, price, payTo/networks and a ready-to-pay best pick |
GET /check/paid?url= (router) | $0.002 USDC (x402): fresh live probe of one endpoint: is it up, latency, the real price and payTo it asks for now |
Examples: examples/ (curl, Python, TypeScript).
| Tool | Cost |
|---|---|
search_x402_endpoints, route_x402_request, get_registry_stats, get_paid_route_requirements | Free |
find_best_x402_endpoint | $0.01 USDC per call |
check_x402_endpoint | $0.002 USDC per call |
Paid tools pay inside the tool call. To enable them:
pip install "x402-router-mcp[pay] @ git+https://github.com/camerxnduff/x402-router-mcp#subdirectory=mcp-server"
export X402_EVM_PRIVATE_KEY=0x... # a dedicated, low-balance Base wallet holding a little USDC export X402_MAX_PAYMENT_USD=0.01 # per-call cap (default 0.01)
Without a key, the paid tools return the price and the x402 payment requirements instead of paying.
x402 v2: Base USDC first, Solana USDC as fallback, settled through the PayAI facilitator.
MIT