Overview

The AI Research Assistant MCP Server brings autonomous research capabilities to AI assistants. The official MCP server for the gpt-researcher project, this server enables AI models to conduct deep research on any topic — searching the web, analyzing academic sources, and generating comprehensive research reports with citations. It's like having a dedicated research analyst available on demand.

Official MCP Server:

The server lives in its own repository, assafelovic/gptr-mcp. gpt-researcher itself is the research library the server calls.

Key Features

🔍

Autonomous Research

Fully autonomous research agent that plans, searches, and synthesizes information without manual intervention

🌐

Multi-Source Aggregation

Searches across web, academic papers, news, and specialized sources for comprehensive coverage

📊

Structured Reports

Generates well-organized research reports with executive summaries, detailed findings, and conclusions

📋

Citation Support

All findings include proper citations and source attribution for verification

🎯

Customizable Depth

Configure research depth from quick overviews to deep, exhaustive analysis

🔄

Iterative Refinement

Research can be refined and expanded with follow-up questions and deeper exploration

Available Tools

Quick Reference

Tool	Purpose
`deep_research`	Perform autonomous web research on a topic
`quick_search`	Run a fast web search returning results with snippets
`write_report`	Generate a report based on research results
`get_research_sources`	Get the sources used in the research
`get_research_context`	Get the full context of the research

Detailed Usage

deep_research▶

Performs autonomous web research on a topic, finding the most reliable and relevant information.

quick_search▶

Performs a fast web search optimized for speed over quality, returning results with snippets.

write_report▶

Generates a report based on research results.

get_research_sources▶

Returns the sources used in the research.

get_research_context▶

Returns the full context of the research.

Installation

The MCP server is the separate gptr-mcp repository. It is not the gpt-researcher PyPI package, which is the research library.

git clone https://github.com/assafelovic/gptr-mcp.git
cd gptr-mcp
pip install -r requirements.txt
cp .env.example .env
# add OPENAI_API_KEY and TAVILY_API_KEY to .env
python server.py

{
  "mcpServers": {
    "research-assistant": {
      "command": "python",
      "args": ["/absolute/path/to/gptr-mcp/server.py"],
      "env": {
        "OPENAI_API_KEY": "your_openai_api_key",
        "TAVILY_API_KEY": "your_tavily_api_key"
      }
    }
  }
}

Python 3.10 or higher is required. An OpenAI API key and a Tavily API key (or another supported search API) are needed.

Use Cases

Literature Review

Ask AI to conduct a comprehensive literature review on any academic topic with cited sources.

Competitive Analysis

Research competitors, market trends, and industry landscapes with structured reports.

Technology Research

Deep dive into emerging technologies, frameworks, and tools with technical analysis.

Fact-Checking

Verify claims, gather supporting evidence, and cross-reference information from multiple sources.

AI Research Assistant MCP Server