"Using RAG to Provide Documentation to LLMs" matching MCP servers:

Enables an agent to run ten ready-made research and monitoring workflows — competitor digests, cited reports, paper alerts, market maps, regulatory and due-diligence watches — pulling from Firecrawl, Tavily, GitHub and landing results in Notion, Slack, Google Docs, Sheets and Linear. Fields are filed with the user's own keys held in the operating system keychain, and every action that creates, sends or changes anything is shown and approved first.

Converts PDF files to text for use with MCP-compatible applications like Cursor IDE.

MCP server that integrates a 1200-paper RAG database with six tools to support research workflows across stages like hypothesis, experiment, statistics, and writing. It routes requests to specialized skills and real-time frontier searches to provide evidence-grounded research mentoring.

Enables Claude Desktop and Claude Code to perform local hybrid semantic and BM25 search over full-text PDFs in a Zotero library, with filters, context retrieval, and citation-backed answers.

Enables MCP clients to safely retrieve and query a RAG system over research papers on Raman spectroscopy of carbon nanotubes using read-only tools, a resource, and a prompt. It adds controlled paid-answer budgeting, prompt-injection fencing, and backend security checks.

Provides retrieval and analysis tools for a quantitative-finance research library, enabling whole-passage answers with verifiable citations, citation checking, entity graph exploration, and corpus inspection.

Enables Claude to search a local hybrid retrieval index of research papers and ingest new PDFs, providing research-paper memory queryable directly through natural language.

Enables creation and management of academic-paper knowledge bases from PDFs, including ingestion, semantic search with reranking, and document-level retrieval via MCP tools.

Enables Claude Code to convert PDF files to high-quality PNG images, download academic papers, and batch process PDFs with automatic folder organization.

Converts Digital Object Identifiers (DOIs) to BibTeX format using the official DOI content negotiation API, enabling users to quickly generate bibliography entries for academic papers.

A local MCP server for evidence-safe academic citation workflows, including verified-reference retrieval, Zotero duplicate detection and import, and Word export via Pandoc with zotero.lua.

This project implements a Model Context Protocol (MCP) server providing Formula One racing data using the Python FastF1 library. Inspired by an existing TypeScript server, it offers similar F1 data functionalities natively in Python via FastF1.

Enables discovering and independently validating scholarly metadata from extracted research text using Crossref, OpenAlex, DataCite, and optional read-only Zotero checks, returning ranked and verified reference candidates.

Enables LLM clients to access crop yield predictions from RGB imagery, topic-based PDF literature, and soil lab/moisture CSV data.

A local-first paper RAG server that enables searching and managing academic PDFs via MCP tools, supporting metadata enrichment and citation graphs.

Enables searching and retrieving UK research grants, award values, institutions, and publications from the UKRI Gateway to Research API without authentication.

Provides AI assistants with access to University of Alabama at Birmingham's Research Computing documentation, enabling users to search and retrieve information about the Cheaha HPC cluster, SLURM job scheduling, storage systems, and available software tools.

Enables offline local LLM analysis of text data via MCP, taking raw text and an instruction to return analysis results without cloud calls.

Enables passage-level semantic search over a Zotero library by extracting, chunking, and embedding PDF text using Gemini and ChromaDB. It provides MCP tools to perform topical searches and retrieve specific document passages with surrounding context.

Exposes seven read-only tools that let an existing chat model search a private, incrementally ingested PDF library, fetch full parent sections with provenance and hash validation, check evidence completeness, audit literal quote anchors, view original PDF pages, and explore a frozen citation snapshot. It provides source-first retrieval and provenance without invoking another model or certifying scientific conclusions.