SciWeave

@DeSci Labs

访问 MCP Server

a month ago

Ground Claude, ChatGPT, Cursor, and Windsurf in 300M scientific works — every citation is a real, verifiable DOI.

概览工具评论

概览

SciWeave MCP

Claude and ChatGPT, grounded in 300 million scientific works. The world's largest open research index, integrated into your AI workflow.

Free to start · usage-based after. Get your API key at mcp.sciweave.com.

Install

Get your API key at mcp.sciweave.com.
Add the server to your client (Claude, ChatGPT, Cursor, Windsurf) using the URL https://mcp.sciweave.com/mcp and your API key as the Authorization Token.
Ask a research question — every claim comes back with a verifiable DOI.

Tools

ask_research_question — AI answer with inline citations grounded in the SciWeave index. Optional min_year / max_year filters.
find_references — Fast lookup. Returns title, authors, year, DOI, URL, and abstract snippet for the top top_k papers. ~1s typical latency, no synthesis.
get_research_thread — Resume a previous research conversation by thread_id (returned by ask_research_question). Original question, answer, citations, and follow-ups.

Every returned paper includes: title, authors, publication year, DOI, URL, abstract snippet.

What it makes possible

Draft a grant introduction or paper background with real citations.
Run a prior-art check before designing an experiment.
Turn a topic into a structured, ranked, cited reading list.
Design a precise search strategy — keywords, boolean queries, year bounds — then run an initial sweep.
Resume a multi-session literature review without losing your citations.

For agent builders

RAG eval harness — pipe ask_research_question into your golden set to benchmark grounding.
Long-horizon literature agent — persist thread_id across runs; resume with get_research_thread.
Citation verification — wrap find_references to post-check any LLM output that mentions a DOI.

Canonical loop: ask_research_question → save the returned thread_id → resume later with get_research_thread.

服务器配置

{
  "mcpServers": {
    "sciweave": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.sciweave.com/mcp"
      ]
    }
  }
}

Build with ShipAny.