MCP server for [SPARKIT](https://sparkit.science), a scientific research agent that searches the literature, reads papers, and returns cited Markdown reports. Submit a question via the `research` tool from Claude Desktop / Cursor / Claude Code; get back a ~90-second cited report without leaving the chat. `uv tool install sparkit-mcp` or `pip install sparkit-mcp`.
Example client config (verify package name in the repo README)
{
"mcpServers": {
"sparkit-mcp": {
"command": "uvx",
"args": ["sparkit-mcp"]
}
}
}Transparent heuristic — same formula for every entry. Total 31/100.
Pre-build reality check for AI coding agents. Scans GitHub, Hacker News, npm, PyPI, and Product Hunt to detect existing competition before building, returning a reality signal score (0-100), duplicate likelihood, similar projects, and pivot hints.
Natural-language patent and scientific literature search across 200M+ patents and 216M+ papers from 170+ jurisdictions, with semantic/BM25 search, structured filters, and record retrieval. Hosted Streamable HTTP endpoint and Dockerized stdio bridge; requires a free Patsnap API key.
MCP server for [ITASCA PFC](https://www.itascacg.com/software/pfc) discrete element simulation — browse documentation, execute scripts, capture plots, and manage long-running tasks via a WebSocket bridge to the PFC GUI.
Research workspace MCP integrating Zotero, Obsidian, and NotebookLM. Search papers (arXiv/Semantic Scholar/PubMed/CrossRef), ingest into Zotero, sync notes to Obsidian, verify NotebookLM briefs. All three external tools optional. `pip install research-hub-pipeline` then `research-hub serve`.
Deep research MCP server for OpenAI Responses API or Open Deep Research (smolagents), with web search and code interpreter support.
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.