Setup guide

Set up ari-mcp-server in Goose

communityunknownunknown

MCP server that stops AI agents from overpaying. Drops into Claude Desktop, Cursor, Continue, Windsurf, Zed, ChatGPT desktop, and Gemini CLI to give any agent live fair-market-value lookups, a green/amber/red prepay verdict, and cryptographically-signed (Ed25519) receipts for every x402 / MPP / agentic-payment quote.

01Configuration

{
  "mcpServers": {
    "ari-mcp-server": {
      "command": "uvx",
      "args": [
        "ari-mcp-server"
      ]
    }
  }
}

Add this to ~/.config/goose/config.yaml. Generated from the captured install method (uvx); the mcpServers shape is shared across Claude Desktop, Cursor, Windsurf, Cline, and VS Code.

02Steps

Make sure Goose is installed and up to date.
Open ~/.config/goose/config.yaml and add the block above (merge into any existing mcpServers).
Provide any required API keys/credentials as environment variables.
Restart Goose and confirm ari-mcp-server’s tools appear.

03Other runtimes

Claude Desktop Cursor Windsurf Cline Continue VS Code OpenAI Agents SDK LangGraph CrewAI

04Provenance

config_sourcegenerated from captured install method

last_checked2026-06-29 07:55Z

sourcesPyPI [p4]

Next step

Ship ari-mcp-server to your agents as a governed Loadout — config, scopes, and approval rules in one place.

Build a Loadout

See also: server page · is it safe? · alternatives