Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
Evidence-backed web research for AI agents. Real-time search with cited claims, confidence scores, and compare mode (raw LLM vs evidence-backed). MCP server, REST API, and Python SDK.
Deep research MCP server for OpenAI Responses API or Open Deep Research (smolagents), with web search and code interpreter support.
Quality signal
44/100 (Fair)
47/100 (Fair)
Install path
npx · high
uvx · high
Engagement
1 0 0 20
4 0 0 96
Tools
Multi-step claim verification pipeline with atomic decompositionHybrid keyword and semantic retrieval with rerankingConfidence scores calibrated from real verification dataMulti-provider parallel search for diverse sourcesContradiction detection and multi-pass consistency checksConfigurable depth modes: fast, thorough, and deep research
Supports OpenAI Responses API with web search and code interpreterCompatible with OpenAI Chat Completions API and experimental ChatGPT Codex subscriptionIntegrates Gemini Deep Research via Interactions APIIncludes Allen AI DR-Tulu and Open Deep Research stack supportConfigurable via TOML file and environment variablesProvides CLI and terminal UI for interactive research and status monitoring
