Skip to main content

MCP server exposing Qonoro's x402 intelligence agents as tools for any MCP-compatible AI agent client.

Project description

qonoro-mcp-server

MCP (Model Context Protocol) server that exposes Qonoro's production x402 intelligence agents as tools, so any MCP-compatible AI agent client can discover and call them directly -- no custom HTTP/x402 client code needed.

This server is a thin, stateless protocol bridge. It contains no business logic and no payment validation of its own: every call is forwarded to the real https://api.qonoro.ai endpoint, and Qonoro's existing production payment_guard validates and settles payment exactly as it does for any direct HTTP/Bazaar caller today.

Tools exposed

Tool Qonoro endpoint Price
qonoro_company_enrich POST /v1/company/enrich $0.25 USDC
qonoro_company_research POST /v1/company/research $2.00 USDC
qonoro_competitors_analyze POST /v1/competitors/analyze $0.50 USDC
qonoro_sales_signals_find POST /v1/sales-signals/find $0.75 USDC
qonoro_person_enrich POST /v1/person/enrich $1.25 USDC
qonoro_revenue_qualify POST /v1/revenue/qualify-lead $0.75 USDC
qonoro_intent_signals_find POST /v1/intent-signals/find $0.75 USDC
qonoro_job_change_detect POST /v1/job-changes/detect $0.50 USDC

How payment works

  1. Call the tool with your normal arguments.
  2. If the tool result contains "payment_required": true, it includes the exact price, network, and pay_to address Qonoro requires.
  3. Sign an x402 payment for that amount/network/address with your own wallet (Qonoro never sees or needs your private key).
  4. Call the tool again with the same arguments plus payment_signature set to your signed value. The server forwards it to Qonoro, which validates and settles it, then returns the real result.

No wallet key, API key, or secret is required to run this MCP server itself -- the only configuration is which Qonoro base URL to call (defaults to production).

Local Development

conda create -n qonoro-mcp python=3.12 -y
conda activate qonoro-mcp
pip install -e ".[dev]"
copy .env.example .env
pytest
qonoro-mcp

This repo has its own Conda environment (qonoro-mcp), same as every other Qonoro backend repo — see docs/01_PROJECT_SETUP_GUIDE.md. Do not install this into a shared/base environment; it isolates the mcp/x402 SDK versions from whatever other Qonoro repos have installed.

Or point an MCP client (Claude Desktop, Cursor, etc.) at:

{
  "mcpServers": {
    "qonoro": {
      "command": "qonoro-mcp"
    }
  }
}

Configuration

See .env.example. There are no secrets to fill in -- QONORO_BASE_URL defaults to https://api.qonoro.ai and only needs overriding for local testing against a dev server.

See AGENTS.md for the payment-bridge design rationale and the checklist for adding a new Qonoro agent to this server.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

qonoro_mcp-0.3.0.tar.gz (11.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

qonoro_mcp-0.3.0-py3-none-any.whl (9.8 kB view details)

Uploaded Python 3

File details

Details for the file qonoro_mcp-0.3.0.tar.gz.

File metadata

  • Download URL: qonoro_mcp-0.3.0.tar.gz
  • Upload date:
  • Size: 11.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.13

File hashes

Hashes for qonoro_mcp-0.3.0.tar.gz
Algorithm Hash digest
SHA256 021260e35ab10de089557220a9f66ec2dc3a1355e09fcc34e3cc83193891d5f1
MD5 5a7dfc08fc6a862da465835af59c8050
BLAKE2b-256 452a0ed26f51920eb30be7e0f430a386b9a9e9e6f51967008a8ed9f5499dc2e8

See more details on using hashes here.

File details

Details for the file qonoro_mcp-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: qonoro_mcp-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 9.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.13

File hashes

Hashes for qonoro_mcp-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 aa6835085f015a2414e4dc88b715747cb099cd47f5b66db7f4bb1e589b7a2a29
MD5 6d6a94dfbea05f2b85a447cb3c90bbab
BLAKE2b-256 186da53b33413e2b3209cde56bff5f204f1cfa9f41d89826eb89866c0e11373b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page