x402search — Pay-Per-Search API Discovery for AI Agents
LocalAbout x402search — Pay-Per-Search API Discovery for AI Agents
x402search is an MCP server for AI agents that discovers x402-enabled HTTP APIs. Searches return endpoint and payment details, with payment made in USDC on Base.
Key features
- 01Search x402-enabled HTTP APIs
- 02Filter by network and price
- 03Limit and rank search results
- 04Return endpoint and payment metadata
Use cases
- 01Find an API for token prices
- 02Discover DeFi and blockchain APIs
- 03Filter APIs by network or cost
MCP support
Exposes the search_x402_apis tool to MCP clients. Each search costs 0.01 USDC on Base and requires an EVM wallet private key.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y x402search-mcpPRIVATE_KEYSecretEVM private key for x402 payment signingLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEx402search MCP Server
Search 14,000+ x402-enabled HTTP APIs from any MCP-compatible agent.
Version: 1.0.3 · License: MIT · Cost: $0.01 USDC per search · Base mainnet · No account needed
npm: https://www.npmjs.com/package/x402search-mcp
PyPI: https://pypi.org/project/x402search-mcp
API: https://x402search.xyz
Requirements
- A wallet private key (EVM)
- USDC on Base mainnet (eip155:8453)
- Get USDC on Base: https://www.coinbase.com/how-to-buy/usdc
Install: Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"x402search": {
"command": "npx",
"args": ["[email protected]"],
"env": {
"EVM_PRIVATE_KEY": "0xYOUR_PRIVATE_KEY_HERE"
}
}
}
}
Config file location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Install: Claude Code
claude mcp add x402search -- npx [email protected]
Then set your key:
export EVM_PRIVATE_KEY=0xYOUR_PRIVATE_KEY_HERE
Install: Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"x402search": {
"command": "npx",
"args": ["[email protected]"],
"env": {
"EVM_PRIVATE_KEY": "0xYOUR_PRIVATE_KEY_HERE"
}
}
}
}
Install: Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"x402search": {
"command": "npx",
"args": ["[email protected]"],
"env": {
"EVM_PRIVATE_KEY": "0xYOUR_PRIVATE_KEY_HERE"
}
}
}
}
Install: Python agents (LangChain, CrewAI, AutoGen, GAME SDK)
pip install x402search-mcp
from x402search import search_x402_apis
results = search_x402_apis(
query="token price API ethereum",
private_key="0xYOUR_PRIVATE_KEY_HERE"
)
print(results)
Full docs: https://pypi.org/project/x402search-mcp
Quick Test
EVM_PRIVATE_KEY=0xYOUR_KEY npx [email protected]
Tool: search_x402_apis
| Parameter | Type | Required | Description |
|---|---|---|---|
| query | string | yes | e.g. "token price API", "DEX swap routing" |
| network | string | no | e.g. "eip155:8453" for Base mainnet |
| max_price_usdc | number | no | Filter to APIs at or below this price |
| limit | number | no | Max results (default 10, max 50) |
Virtuals ACP Integration
x402search is available as a native ACP agent on the Virtuals protocol marketplace.
- Agent ID: 22531
- Agent profile: https://app.virtuals.io/acp/agent-details/22531
- Job name:
x402search - Price: 0.01 USDC per search
- Accepts crypto, DeFi, and blockchain API discovery queries
- Rejects off-topic requests automatically at the request phase
- Returns structured results: endpoint URLs, payment metadata, network, and relevance rank
Links
- npm: https://www.npmjs.com/package/x402search-mcp
- PyPI: https://pypi.org/project/x402search-mcp
- API: https://x402search.xyz
- Health: https://x402search.xyz/health
- GitHub: https://github.com/x402-index/x402search-mcp
- x402 protocol: https://x402.org
Comments
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.