SciWeave

Created By

DeSci Labsa month ago

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

Overview

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.

Server Config

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

Recommend Servers

TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.

Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

Howtocook Mcp基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server，帮你推荐菜谱、规划膳食，解决“今天吃什么“的世纪难题； Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"

BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.

WindsurfThe new purpose-built IDE to harness magic

DeepChatYour AI Partner on Desktop

ChatWiseThe second fastest AI chatbot™

Serper MCP ServerA Serper MCP Server

MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs

Tavily Mcp

Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.