Autonomous Web Research Agent

A teaching project: one Python agent that plans, searches the web, stores notes in RAG, writes a report, then critiques itself and loops until the answer is good enough.

Stack: Python 3.11+ · LangChain · LangGraph · MCP · Chroma RAG · LangSmith

What you are building (classroom map)

Read TEACHING.md for the full lesson.

Related MCP server: Local-MCP-server

Setup

cd ~/Projects/autonomous-web-research-agent
python3.11 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
cp .env.example .env

Put at least one LLM key in .env (OPENAI_API_KEY is the default path). Search works with free DuckDuckGo. Add TAVILY_API_KEY later if you want higher-quality search. Add LANGCHAIN_API_KEY to watch traces in LangSmith.

Run a research job

python -m research_agent.cli "How does MCP differ from a normal LangChain tool?"

Run the backend

python -m research_agent.api
# POST http://127.0.0.1:8001/research  {"question": "..."}

Run the MCP server (for Cursor / other hosts)

python -m research_agent.mcp_server

Example Cursor MCP config:

{
  "mcpServers": {
    "research-tools": {
      "command": "/Users/YOU/Projects/autonomous-web-research-agent/.venv/bin/python",
      "args": ["-m", "research_agent.mcp_server"]
    }
  }
}

Tests (no API key needed)

pytest