A local, rule-based MCP server for searching and analyzing academic papers from arXiv. Enables paper search, ranking, smart summarization, keyword extraction, and citation generation without API keys or LLM calls.
A local-first MCP server that analyzes research papers, maps citation graphs, and surfaces insights with verbatim-verified contradictions, all while keeping data private on your machine.
Metis — an open-source (AGPL-3.0), local-first MCP server / research companion. It answers from the user's own indexed PDF library with page-level citations (and flags what it can't find rather than inventing), keeps all data on the user's machine, and routes requests to 34 specialist agents.
Local-first knowledge retrieval MCP server that turns private text documents into a source-backed knowledge base, enabling retrieval, comparison, summaries, and review outlines for any local MCP client while keeping source paths and index operations visible.
A local-first MCP server for building and querying PDF knowledge bases. It indexes PDFs into DuckDB and exposes evidence-grounded retrieval tools to separate corpus-backed answers from independent reasoning.
Local-first MCP server for indexing and searching research materials (papers, notes, logs, READMEs) using SQLite FTS, with tools for memory management and evidence retrieval.
