research-agent
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@research-agentSearch the web for the latest research on AI agents"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Research Agent
A practical Python research agent that searches the web with Tavily, organizes results through LangGraph, and uses OpenAI to produce a structured Markdown research report. An MCP server exposes the web-search capability for MCP clients and the MCP Inspector.
Features
Real web search with Tavily
LangGraph workflow: research -> summarize
OpenAI-based report generation
Structured findings, analysis, and sources
Automatic Markdown report saving in
reports/MCP tools:
helloandweb_searchBasic automated tests with pytest
Secrets excluded from Git with
.gitignore
Related MCP server: AI Makerspace MCP Demo Server
Architecture
User question
|
v
LangGraph
|
v
Tavily web search
|
v
Source normalization
|
v
OpenAI synthesis
|
v
Markdown reportRequirements
Python 3.11+
A Tavily API key
An OpenAI API key
Setup on Windows
From the project folder:
python -m venv .venv
.venv\Scripts\activate
pip install -r requirements.txtCreate .env from .env.example and add your own API keys. Never commit .env.
Run
python -m app.mainEnter a research question. The report is printed in the terminal and saved under reports/.
MCP Inspector
Start the MCP Inspector from the project root:
mcp dev mcp_server\server.pyThe server exposes:
hello(name)web_search(query)
Tests
Run the test suite with:
pytest -qThe tests are designed to validate parsing, report saving, and state structure without requiring a live API request.
Project structure
research-agent-final/
|-- app/
| |-- agent.py
| |-- config.py
| |-- graph.py
| |-- main.py
| `-- state.py
|-- mcp_server/
| |-- server.py
| `-- tools.py
|-- tests/
|-- .env.example
|-- .gitignore
|-- README.md
`-- requirements.txtGitHub checklist
Before pushing to GitHub:
Confirm
.envis not tracked.Confirm
.venv/,__pycache__/,.pytest_cache/, andreports/are ignored.Run
pytest -q.Add the project files to Git and make the first commit.
Example:
git init
git status
git add .
git commit -m "Initial research agent"Do not run git add .env.
Security
API keys belong only in .env or another secret manager. Keep .env out of GitHub and do not paste API keys into chat or source files.
This server cannot be deployed
Maintenance
Related MCP Connectors
Search, vet & assemble MCP servers from your agent: verified tools, risk labels, and trust scores.
Scrape, crawl and search the web for AI agents via MCP.
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
Related MCP Servers
- FlicenseCqualityDmaintenanceEnables web search capabilities through the Tavily API. Allows users to search the web for information using natural language queries through the MCP protocol.3-
- FlicenseAqualityDmaintenanceEnables web search capabilities through the Tavily API and serves as a demonstration platform for building custom MCP tools. Designed for educational purposes to showcase MCP server development and LangGraph integration.6-
- FlicenseNot gradedqualityDmaintenanceEnables file system operations, web scraping, and AI-powered search through MCP tools for use by LLM agents.1-
- FlicenseNot gradedqualityCmaintenanceMCP server exposing 8 Tavily tools (web search, fetch, crawl, map, QnA, context, and deep research) via Streamable HTTP for AI assistants to perform live web retrieval and research.1-