📖 Read-only mirror. aimarket-mcp is published from the canonical AI-Factory monorepo. Pull requests are not accepted — any commit pushed here is overwritten by scripts/mirror_satellites.sh on the next sync. 🐞 Found a bug or have a request? Please open an issue.

aimarket-mcp — ecosystem MCP gateway

One MCP gateway. Three hardened tools. Shared by Metis, ARGUS, and the ecosystem.

Transport: stdio (mcp_stdio_server.py) for Glama / Claude Desktop / Cursor, built with the official Model Context Protocol Python SDK (mcp, FastMCP). Also ships Streamable-HTTP on :9090 for self-hosted deployments (aimarket-mcp-http, Docker Compose).

Compatible hosts: Claude Desktop, Cursor, Glama, and any MCP client that supports stdio or Streamable-HTTP.

Tools

Why a gateway (not per-agent tools): generic capabilities are written once; the security core lives in one audited place. Ecosystem-specific capabilities live in their own MCP servers (aimarket-oracle-gateway, aimarket-plugins).

Configure (env)

Run (stdio — Glama / Claude Desktop)

pip install -e .
python mcp_stdio_server.py

Claude Desktop (mcpServers entry):

{
  "mcpServers": {
    "aimarket-mcp": {
      "command": "python",
      "args": ["mcp_stdio_server.py"],
      "cwd": "/path/to/aimarket-mcp"
    }
  }
}

Or via PyPI script: aimarket-mcp

Run (HTTP — self-host)

pip install -e .
AIMARKET_MCP_KEY=sk-... AIMARKET_MCP_PRODUCTION=1 aimarket-mcp-http   # :9090
# or: docker compose up -d   (uses Dockerfile.http)

Cursor / Claude (Streamable HTTP)

{
  "mcpServers": {
    "aimarket-web": {
      "type": "streamable-http",
      "url": "http://127.0.0.1:9090/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_AIMARKET_MCP_KEY"
      }
    }
  }
}

Publish on Glama

Listing: glama.ai/mcp/servers/alexar76/aimarket-mcp

Same pattern as aimarket-oracle-gateway (working on Glama): repo-root glama.json + Dockerfile + python mcp_stdio_server.py.

Do not use the auto-generated debian:trixie-slim + uv sync + mcp-proxy -- aimarket-mcp template — that was the broken HTTP/ENOENT path.

Consumers

• Metis — enable the preset:
  hljs language-yaml

  Copy

  enable_mcp_tools: true
  mcp_ecosystem_presets: [aimarket-web]
  

• ARGUS — add the server to argus.config.json mcpServers (see that repo).

Test

pip install -e '.[dev]' && pytest -q

Glama

Glama ignores repo Dockerfiles — set Build steps in admin/dockerfile:

["bash scripts/glama_install.sh"]

CMD: [".venv/bin/python", "mcp_stdio_server.py"]. Pin main or tag glama-build (not a fixed SHA). Details: docs/GLAMA.md.

Registries