MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
doc-ingest-mcpgithub.com/aeewws/doc-ingest-mcpupdated this year
CLI and MCP server for document ingestion with Docling
MIT -
markitdown-ingest-marketplacegithub.com/pjtahiliani/markitdown-ingest-marketplaceupdated this year
Portable, privacy-focused MarkItDown document ingestion plugin and marketplace for Codex on macOS
MIT -
Vectorless tree-reasoning RAG document-ingestion platform exposed over the Model Context Protocol (MCP). Structural queries over inspectable document trees — no vector DB required. Docs: https://ingestion-loop.pageindex.aiwithsalil.work
-
volterra-knowledge-enginegithub.com/duhman/volterra-knowledge-engineupdated this year
Enterprise Document Ingestion with AI Embeddings — Multi-source ingestion pipeline with pgvector, GDPR compliance, and MCP server
MIT -
mempalace-extendedgithub.com/qudadd/mempalace-extendedupdated this year
Extension of the original MemPalace with document ingestion, image assets, MCP tooling, and folder watch.
MIT ★ 1 -
SIVE (Scrap Ingest Vectorize Extends): documentation ingestion, vector indexing and MCP retrieval
pypi MIT -
Production-ready MCP server for document ingestion and knowledge management with vector search. Supports PDF, DOCX, TXT, MD, CSV, JSON, HTML with ChromaDB and multiple embedding providers.
npm MIT -
document-parser-mcpgithub.com/kgand/document-parser-mcpupdated this year
lightweight MCP server for universal document ingestion into parsable Markdown
MIT ★ 2 -
aibraingithub.com/sindecker/aibrainupdated this year
AI agent brain with memory, teams, flows, document ingestion, and MCP — your agent, but better every day
pypi Proprietary -
docsyncgithub.com/Lahari-V03/docsyncupdated this year
Multi-source document ingestion pipeline to ingest digital PDFs, scanned PDFs (Azure OCR), and JSON exports into a unified PostgreSQL + pgvector schema with semantic search via FastAPI and MCP tools for Cursor/Claude Desktop.
-
custom-docs-mcpgithub.com/lecieletoile/custom-docs-mcpupdated this year
MCP server that ingests Git-hosted documentation and enables semantic search
pypi BSD-3-Clause -
nowdocsgithub.com/nowdocs/nowdocsupdated this year
Single-binary MCP documentation server for LLM coding agents — ingest, chunk, embed, and retrieve docs locally
cargo MIT OR Apache-2.0 -
@moxellabs/atlasgithub.com/moxellabs/atlasupdated this year
Local-first documentation ingestion, retrieval, and MCP/server access for multi-repo engineering docs.
npm AGPL-3.0-or-later -
opengroundgithub.com/poweroutlet2/opengroundupdated this year
Ingest official documentation into a local vector database and expose it via MCP for AI coding agents
pypi MIT -
graphiti-influxer-publicgithub.com/Milofax/graphiti-influxer-publicupdated this year
Ingest documents into Graphiti Knowledge Graph via MCP
MIT -
file-vault-mcpupdated this year
Local-first MCP knowledge base with web documentation ingestion. Store, search, and crawl docs — fully offline-first.
npm -
GitHub-Documentation-Rag-Agentgithub.com/Mandoa-Labs/GitHub-Documentation-Rag-Agentupdated this year
RAG agent that ingests GitHub's official documentation, embeds it with local Ollama LLMs, and serves semantic search via a PostgreSQL pgvector database.
-
RAG3github.com/nyamx/RAG3active
Local document search with GPU-aware ingestion, hybrid retrieval, desktop UI, and MCP access from Codex and ChatGPT web.
MIT -
documentIngestionRoutergithub.com/derekbmoore/documentIngestionRouterupdated this year
Standalone MCP server for intelligent document ingestion, classification, and TriSearch™ indexing
MIT -
MCP server which leverages a FastAPI application to ingest documents using Unstructured
-
Go web crawler to scrape documentation sites and convert content to clean Markdown for LLM ingestion (RAG, training data)
go Apache-2.0 ★ 110 -
mcpdocmindgithub.com/vnashchokin/mcp-docmindupdated this year
Interactive installer for McpDocMind — MCP server for .NET API documentation search. Ingests .NET DLLs, Markdown, Git repos into local SQLite and exposes hybrid search via Model Context Protocol.
nuget MIT -
docflowgithub.com/jajimenez/docflowupdated this year
Documentation ingestion pipelines and MCP knowledge base server for AI agents
MIT -
Serverless private knowledge base backend on AWS with document ingestion, OCR, chunking, vector indexing, and MCP access.
GPL-3.0 -
Multi-tenant RAG and MCP document intelligence platform with secure PDF ingestion, tenant-isolated Qdrant retrieval, Groq-powered grounded answers, and a Flask web application.
-
Personal MCP server for portable LLM context — semantic search, structured facts, and document ingestion backed by PostgreSQL + pgvector
-
Universal document ingestion engine — any file in, agent-ready Markdown out. PDF, Word, PowerPoint, Excel, HTML, EPUB and more, with structure preserved, page anchors you can cite, and an MCP server. No LLM in the conversion path.
Apache-2.0 -
docsearchgithub.com/ypngslo/docsearchupdated this year
Self-hosted document search: local ingestion + pgvector retrieval pipeline, web console, and a ChatGPT MCP connector
MIT -
RAG document-search MCP server with pluggable SQLite FTS5 / Chroma backends and incremental ingestion
MIT -
bitwise-mcpgithub.com/MichaelAyles/bitwise-mcpupdated this year
MCP documentation server for embedded developers. Ingests PDF reference manuals (1000+ pages), extracts register definitions, and provides fast semantic search with minimal token usage.
MIT ★ 14 -
MCP server over the Liara cloud documentation: hybrid Persian/English retrieval, page reads, deployment config and build-log diagnosis. Corpus ships in the package, so no ingest, no database and no API key.
MIT -
A local-first, open-source knowledge engine for document ingestion, retrieval, grounded synthesis, citations, and MCP.
-
Repo-MCP is a NiceGUI-based application designed to ingest GitHub repository documentation and enable interactive Q&A using Retrieval Augmented Generation (RAG).
-
MCP server exposing GreenNode RAG APIs (knowledge bases, documents, search, ingest) over stdio or streamable HTTP.
npm Apache-2.0 -
Local RAG system with realtime auto ingestion of documents and notes and exposed via MCP to be used with Local or Cloud based LLMs
★ 6 -
@plugsky/mcpactive
Plugsky MCP server — 36 models, RAG knowledge search, platform tools and document ingestion for Claude, Cursor, VS Code, Windsurf, Zed.
npm MIT -
atlas_mcpgithub.com/rsanandres/atlas_mcpupdated this year
A Model Context Protocol (MCP) server exposing healthcare AI tools for RAG-powered clinical queries, document reranking, and FHIR data ingestion.
pypi MIT ★ 1 -
Document-centric RAG platform with ingestion, hybrid retrieval, MCP integration, admin tooling, and a separate local-first search UI called RAGfind.
MIT ★ 2 -
2ndbraingithub.com/mull2536/2ndbrainupdated this year
Local Windows-native MCP server giving Claude Code verbatim cross-session recall - SQLite FTS5 over session transcripts, memory files and documents. Zero external LLM calls, credential redaction at ingest.
-
MCP server for per-customer PDF document management and RAG. Ingests text, scanned and chart-heavy PDFs (PyMuPDF + Tesseract + vision model), isolates each customer in its own Qdrant collection, and returns cited answers with deep links to the original PDF page. Local-first with Ollama, or any OpenAI-compatible API.
MIT -
Ts RAG system. ingest documents, creates embeddings, stores in pgvector and query through cli or mcp server. fully local with node-llama-cpp
★ 1 -
ontoramp-knowledge-cartographergithub.com/ontoramp/ontoramp-knowledge-cartographerupdated this year
Ingest documents into a governed knowledge graph accessible to any AI agent. Returns knowledge health scores and coverage maps. Free read tier.
MIT -
mcp-docqa-servergithub.com/saivarun161/mcp-docqa-serverupdated this year
MCP server for document Q&A — the retrieval half of RAG as reusable infrastructure: semantic search over pgvector/SQLite, OpenAI or keyless embeddings, PubMed ingestion, recall-gated CI
MIT -
Collective AI memory for multi-agent teams. 10-stage GAMR search engine, knowledge graph (Apache AGE), document ingestion, 40 MCP tools.
NOASSERTION ★ 11 -
kglite-docsgithub.com/kkollsga/kglite-docsupdated this year
Agent-first knowledge base for documents. Built on kglite + BAAI/bge-m3. Multi-format ingest, cross-checked summaries, review kanban, grounding checks, and an MCP server.
pypi MIT -
Pharos — local-first agentic RAG for your team's document library: multi-format ingest, hybrid retrieval, enterprise ACL, dual HTTP + MCP exits.
MIT ★ 241 -
Local-first text runtime for agents: ingest, structure, annotate, and search documents with UUID-stable identity, W3C Web Annotations, and content-addressed persistence. Rust engine + MCP server.
Apache-2.0 -
Official Claix guide. The security layer between your SQL database and AI agents: controlled retrieval, Guard checks on INSERT/UPDATE/DELETE, and document ingest. REST, MCP, and A2A.
★ 3 -
MCP server for local-first document knowledge bases: LanceDB hybrid search (bge-m3 + CrossEncoder rerank), native BM25 with jieba, and PDF-to-LaTeX ingestion via a local MinerU pipeline
MIT -
DOCBasegithub.com/Max-Walka/DOCBaseupdated this year
A RAG-powered knowledge base that ingests documents, stores them as vectors, and lets Claude answer questions over them. Exposed as an MCP server so Claude Desktop and Claude Code can query it natively. Web UI on top for demos.
-
Local-first RAG MCP server in Python: hybrid search (semantic + BM25 keyword boost) over your own documents. 11 MCP tools + CLI, markitdown ingestion for 12 formats, multilingual embeddings, LanceDB. Nothing leaves your machine.
pypi MIT ★ 60 -
ragentgithub.com/ca-srg/ragentupdated this year
CLI tool for building production RAG systems from Markdown, CSV, and PDF documents using hybrid search (BM25 + vector) with OpenSearch. Features MCP server, Slack bot, Web UI, multi-source ingestion (local/S3/GitHub), and multi-provider embeddings (Bedrock/Gemini).
NOASSERTION ★ 13 -
CoreRaggithub.com/TJ-Neary/CoreRagupdated this year
Local-first knowledge engine with semantic search, GraphRAG, and Claude Desktop integration via MCP. Features hybrid search (vector + BM25), cross-encoder reranking, multi-format document ingestion (PDF, DOCX, audio, video), and privacy-preserving PII detection. Apple Silicon optimized.
MIT ★ 1 -
AndroidAgenticWikigithub.com/trinadhthatakula/AndroidAgenticWikiupdated this year
A Git-backed knowledge graph and Model Context Protocol (MCP) server for Android Studio. Equips AI agents with strict architectural rules, official Google skills, and an autonomous documentation ingestion pipeline to eliminate code hallucinations.
★ 1 -
Local RAG archive of your calls: faster-whisper transcription, pyannote diarization, entity graph and tasks, hybrid vector search with an "ask the archive" chat, live call co-pilot, Telegram and document ingestion, MCP server for Claude. Runs on your machine.
MIT ★ 2 -
Custom MCP Server with RAG, Weather, Brave Search & Notes — A fully featured MCP server built with FastMCP, integrating OpenAI models, GroundX RAG capabilities, Brave News Search, Weather API, and local notes handling. Designed for developers to run intelligent multi-agent systems with semantic search, document ingestion,and LLM-based interactions.
MIT -
Self-hosted MCP server running multi-step Claude agent pipelines: ingest artifacts into reusable knowledge bases, generate structured documents (SOW/BRD/HLD) and configs (JSON/YAML/XML), write SDK integration code from API docs, automate workflows on API-less websites via browser, and execute live API sequences from specs.
NOASSERTION -
docsite-ingest-mcpgithub.com/talan-digital-factory/docsite-ingest-mcpupdated this year
Scrape documentation websites, index in Chroma, expose retrieval through MCP
pypi MIT -
ai-docs-vector-db-hybrid-scrapergithub.com/BjornMelin/ai-docs-vector-db-hybrid-scraperupdated this year
Retrieval-augmented docs ingestion stack: Firecrawl + Crawl4AI + Qdrant vector search with FastAPI and MCP interfaces for AI engineers.
MIT ★ 11 -
Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
pypi MIT ★ 660