Multi-MCP AI Assistant

Overview

A small assistant that gathers tools from several MCP servers into one list. Tools from the github, k8s and db namespaces are listed through GET /tools and invoked through POST /call, and any apply operation is refused. A versioned /v1 ops API adds workspaces, tenant isolation, job approval and audit records.

• Built with: Python, pytest, GitHub Actions

• Scope: Local laptop lab with tests; it does not call a hosted model or apply production changes.

Related MCP server: MCP

Project guide

Project architecture · Interview questions and answers

Use the architecture document for the component diagram, implementation boundaries, and verification entry points. The interview guide includes source-backed answers and project walkthroughs.

Implementation map

Local setup and verification

From the repository root (the commands follow the checked-in manifests):

python3 -m venv .venv
source .venv/bin/activate
python -m pip install -r requirements.txt
python -m pytest -q

To serve the FastAPI application locally, install the server separately if it is not already available:

python -m pip install uvicorn
PYTHONPATH=src python -m uvicorn multimcp.main:app --reload

Level: 10 — MCP & Tool-Using Agents

Skills: Python, several MCP servers in one list

Tools from github, k8s, and db namespaces. Apply refused.

pip install -r requirements.txt
pytest -q

This is a local laptop proof. It does not call a hosted model and it does not apply production changes.

Ops plane

Workspaces, tenant isolation, job approval, and audit live under /v1. Production apply is refused. See docs/ARCHITECTURE.md.

Documentation checks

Project architecture, interview guides, and local source links are checked automatically on pushes and pull requests. Run the same check locally:

python3 .github/scripts/validate_project_docs.py

See service improvements and local run instructions.