{"id":"gptr-mcp","name":"GPT Researcher MCP Server","homepage":"https://github.com/assafelovic/gptr-mcp","repo_url":"https://github.com/assafelovic/gptr-mcp","category":"ai-ml","subcategories":["research","mcp-server","web-search"],"tags":["deep-research","mcp","autonomous-agent","tavily","python","claude-desktop","sse","stdio"],"what_it_does":"MCP server wrapper around GPT Researcher that exposes deep research, quick search, report writing, and source retrieval as MCP tools. Supports STDIO, SSE, and Streamable HTTP transports for integration with Claude Desktop and other MCP clients.","use_cases":["Deep research from within Claude Desktop or other MCP clients","Automated report generation with cited sources via MCP protocol","Investment and market research integrated into AI workflows","n8n workflow automation with deep research capabilities","Source validation and fact-checking within agent pipelines"],"not_for":["Sub-second search results - deep research takes ~30-40 seconds","Environments without Python 3.11+","Use cases that don't need MCP protocol (use gpt-researcher directly)","Offline or air-gapped environments"],"best_when":"You want deep, multi-source research accessible as MCP tools from Claude Desktop or other MCP-compatible clients, and can tolerate 30-40 second response times.","avoid_when":"You need instant search results, don't use MCP-compatible clients, or want to avoid managing API keys for OpenAI and Tavily.","alternatives":[{"name":"gpt-researcher","note":"The underlying library; use directly if you don't need MCP"},{"name":"Tavily MCP","note":"Simpler web search MCP without autonomous research orchestration"},{"name":"Exa MCP","note":"Neural search MCP server, faster but less depth"}],"af_score":59.9,"security_score":55.0,"reliability_score":null,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":"unknown","last_evaluated":"2026-03-01T09:50:05.651294+00:00","performance":{"latency_p50_ms":35000,"latency_p99_ms":120000,"uptime_sla_percent":null,"rate_limits":"Dependent on upstream API rate limits","data_source":"llm_estimated","measured_on":null}}