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.
-
@harrylabs/llm-knowledge-basesupdated this year
Representation-first multimodal Markdown wiki runtime for Obsidian vaults, with standalone CLI, MCP server, and OpenClaw compatibility.
npm MIT -
MCP server providing a persistent markdown knowledge base with hybrid dense + sparse vector search (Qdrant, Cloudflare Workers AI, Splade).
-
Your First LLM-Wiki Conversation Knowledge Base
oci Apache-2.0 ★ 454 -
Persistent, searchable knowledge base for Large Language Models
★ 5 -
MemoGraphgithub.com/Indhar01/MemoGraphupdated this year
MemoGraph is an intelligent personal memory management system for Large Language Models (LLMs) that transforms markdown notes into a queryable, graph-based knowledge base. It enables LLMs to access contextually relevant information from your personal knowledge vault using hybrid retrieval techniques.
pypi MIT ★ 4 -
KnowledgeManager_MCPgithub.com/Big-ShahMir/KnowledgeManager_MCPupdated this year
A highly efficient local server that implements the Model Context Protocol (MCP). It acts as a bridge, providing Large Language Models (LLMs) with direct, tool-based access to a curated knowledge base built from local PDF documents.
-
persistant-knowledge-base-mpcgithub.com/Basavarajrp/persistant-knowledge-base-mpcupdated this year
This is MCP project for conneting all LLMs to have single persistant knowledge base.
-
The Karpathy LLM Wiki, production-ready. Zero-RAG personal knowledge base with MCP server, multi-agent support, knowledge graph visualization, and hallucination enforcement. No embeddings, no vector DBs — just markdown + git.
★ 5 -
arkongithub.com/nduckmink/arkonupdated this year
Arkon: Enterprise AI Knowledge Hub & MCP Server. Self-hosted knowledge base for teams to manage RAG contexts, access policies, and AI skills. Connect Claude and other LLMs via Model Context Protocol (MCP) for automated, secure organizational knowledge integration.
NOASSERTION ★ 1,522 -
A minimalist, file-based knowledge base server (MCP) for LLMs.
npm MIT -
memory-wikigithub.com/algiras/memory-wikiupdated this year
A local-first, semantic knowledge base and MCP server for LLMs.
cargo MIT -
Modular Context | Karpathy LLM Knowledge Base + Gmail & G-Cal — multi-account MCP server for Claude Code, encrypted local-first
★ 102 -
vouch-kbgithub.com/plind-junior/vouchupdated this year
Git-native, review-gated knowledge base for LLM agents. MCP server + CLI.
pypi MIT -
🧠 CLI-first knowledge base & second brain for LLMs (Obsidian-style Markdown, wikilinks, core/brain memory, and MCP server)
MIT ★ 1 -
A production-grade knowledge base operating system — AI agents compile raw sources into persistent, cross-linked Markdown wikis with concurrency control, multi-provider LLM integration, FTS5 search, and community detection. One repo. Any agent. Any machine.
pypi MIT ★ 3 -
BrainAIgithub.com/BrezhnevEugen/BrainAIupdated this year
Native macOS personal knowledge base with AI — LightRAG knowledge graph, RAG chat, SpriteKit graph viewer, MCP bridge, 6 LLM providers. Privacy-first: your data stays local.
Apache-2.0 ★ 4 -
Turn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, self-hosted.
go MIT ★ 153 -
@formbay/knowledge-mcpgit+https://gitlab.formbay.com.au/ink-design-system/knowledge-vault.gitupdated this year
MCP server exposing the Formbay Knowledge Base to LLM tools (Cursor, Claude, Claude Code).
npm UNLICENSED -
A local-first LLM knowledge-base engine that compiles documents into an OKF-conformant, citation-backed wiki
pypi Apache-2.0 ★ 6 -
edgenote-aigithub.com/0xkaz/edgenote-aiupdated this year
Shared knowledge base for humans and LLMs on Cloudflare Workers, accessible via MCP, REST API, and Web UI
MIT ★ 3 -
LAN web UI + job runner for okforge knowledge bases: scanned PDF -> VLM OCR -> translated, page-cited LLM wiki. Serial job queue, MCP server, Quartz publishing.
MIT ★ 5 -
Self-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cpp), multimodal ingestion (vision, audio transcription, speaker diarization), and knowledge graph. Rust + PostgreSQL.
NOASSERTION ★ 30 -
AnticLawgithub.com/Goga74/AnticLawupdated this year
LawMemory. Local-first knowledge base for LLM conversations. Folder = project, file = chat. Import from Claude & ChatGPT, search across everything, connect to Claude Code via MCP. Your disk is the source of truth — no cloud required.
MIT ★ 1 -
Civoragithub.com/emanuelbenavile/Civoraupdated this year
Knowledge base and MCP server that keeps project knowledge readable by LLMs.
-
A hierarchical Markdown knowledge base with MCP access for LLM agents like Claude and Cursor — validate, sync to MS SQL Server, search via MCP.
MIT -
Ultra-lightweight local knowledge base (OKF v0.2 / LLM Wiki). Markdown is the source of truth; agents connect over MCP — Claude Code, Codex, Cursor, Strata, Unsloth and more.
MIT ★ 4 -
Key-free MCP servers that let LLMs build real TouchDesigner networks: local knowledge base (no API keys), offline .toe/.tox generation, live TD editing. Eval-gated - 636/636 build-token-exact.
AGPL-3.0 ★ 1 -
@sidleo3/codex-wikiactive
Codex plugin for the llm-wiki knowledge base: bundled skill, 14 wiki_* MCP tools, and session-time APPEND_SYSTEM_PROMPT.md rule injection. Self-contained and shared with DSH / Pi / MCP / Skill forms.
npm MIT -
Local-first, LLM-curated personal knowledge base + Claude Code plugin: research topics, compile cited articles, and query with hybrid retrieval — on your Claude subscription or an Anthropic API key.
MIT -
@agent-wiki/mcpgithub.com/xinhuagu/agent-gitupdated this year
Agent-driven knowledge base — immutable raw sources + mutable wiki + self-checking lint. MCP server, no LLM needed.
npm MIT -
src-to-kbgithub.com/vezlo/src-to-kbupdated this year
Convert source code to LLM ready knowledge base
npm NOASSERTION ★ 40 -
tomegithub.com/zsembek/tomeupdated this year
Agent-native knowledge OS: turn messy PDFs, scans & DOCX into a verifiable, Markdown knowledge base that LLMs & AI agents read, search and curate — over REST, MCP and a React Library UI.
MIT ★ 2 -
mcp-server-atlassian-confluencegithub.com/aashari/mcp-server-atlassian-confluenceupdated this year
Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.
npm ★ 63 -
Local-first GraphRAG over a markdown knowledge base: LightRAG, Ollama/Qwen, MCP server, LLM router, scheduled self-maintenance
MIT -
Semantic, persistent knowledge graph memory for LLM-based and multi-agent systems, exposed via the Model Context Protocol (MCP).
MIT ★ 4 -
Offline AI knowledge base: read, search and ask your ZIM library (Wikipedia and the Kiwix catalog) with a local or hosted model, and serve it to LLM apps over MCP.
pypi GPL-3.0-only -
FlyArchive — self-hosted personal document archive and knowledge base with hybrid semantic + full-text search. Local-first RAG: an MCP server gives Claude, Codex and any LLM agent search and document tools over your files, mail and scans. Strict intake, access tokens, nothing leaves your machine.
AGPL-3.0 -
hermes-knowledge-enginegithub.com/ginaseo/hermes-knowledge-engineupdated this year
Personal knowledge pipeline — turns Slack conversations and Claude Code sessions into a structured, LLM-enriched Obsidian knowledge base, queryable via MCP.
-
swarmvaultgithub.com/swarmclawai/swarmvaultupdated this year
The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal knowledge management, AI second brain, and durable Claude Code / Codex / OpenClaw memory.
npm MIT ★ 736 -
Project-aware collection management based on Qdrant, including a Rust MCP, daemon and CLI: hybrid semantic, pattern and full-text (FTS5) search into single or cross-concerns collection. Dedicated collections for knowledge library, LLM behavioral rules, and an LLM scratchpad
pypi Apache-2.0 ★ 4 -
Your team's knowledge base is also your AI's memory. Shared markdown notes with [[links]], semantic search and SSO, used by Claude and other assistants over MCP. No LLM on the server.
MIT ★ 1 -
Self-hosted multi-agent AI orchestration demo: n8n, MCP server, LLM routing, self-updating knowledge base
MIT -
MCP server for the XKnow Knowledge Base — search and explore curated SEO, SaaS, and LLM-wiki knowledge from any AI agent. Local, no API key, MIT.
npm MIT -
Local-first personal knowledge base CLI — hybrid FTS + pgvector search, a GraphRAG entity graph, and LLM enrichment over your notes, transcripts, Slack & Gmail. Runs fully local on Ollama (no cloud, no API keys); queryable by any AI agent through the built-in MCP server. Postgres-backed, publishes an Obsidian-style Quartz wiki.
pypi MIT ★ 17 -
@guqings/exoupdated this year
Your exocortex. Ingest ChatGPT exports, PDFs, and files into a searchable knowledge base. Hybrid FTS5 + vector search. LLM-compiled knowledge pages. MCP server for Claude Code and Cursor.
npm MIT -
Semantic knowledge base for DS 2.x Wiki — vector history, MCP server for LLM access
MIT -
Web scraper & crawler → clean Markdown with byte-level SHA-256 provenance + WARC archival for LLM/RAG knowledge bases
pypi MIT ★ 2 -
Practical LLM-powered search engine and knowledge base framework with real-time search and agent support, built with SpringAI, RAG, DeepSeek, Dify, Ollama, and Xinference.
-
LLM agent for business websites: answers from a knowledge base, captures leads · OpenTelemetry GenAI tracing, evals, MCP server · FastAPI · RU/EN/AR
-
Model Context Protocol (MCP) server designed for LLMs to interact with Obsidian vaults. Provides secure, token-aware tools for seamless knowledge base management through a standardized interface.
npm Apache-2.0 -
A Model Context Protocol (MCP) server that connects AI models to GROWI wiki content. Enables LLMs to search and retrieve information from your organization's knowledge base for accurate, context-aware responses.
npm MIT -
A production-ready Telegram-to-LLM bridge powered by OpenRouter, featuring persistent SQLite chat history, local Markdown wiki knowledge bases, MCP tools, and hot-reloadable configurations.
-
Unofficial LLM-ready knowledge base for Grow / Meshulam (גרואו · משולם) payments — the Light API as llms.txt + MCP server + merged OpenAPI & Postman. Not affiliated with Grow/Meshulam.
NOASSERTION ★ 3 -
code-security-skillgithub.com/Chiehyii/code-security-skillupdated this year
Secure-coding knowledge base and MCP server for AI coding assistants, covering OWASP Top 10, ASVS, CWE, API, LLM, and supply-chain security.
-
@iflow-mcp/growilabs-growi-mcp-serverupdated this year
A Model Context Protocol (MCP) server that connects AI models to GROWI wiki content. Enables LLMs to search and retrieve information from your organization's knowledge base for accurate, context-aware responses.
npm MIT -
brimminggithub.com/Tight-Line/brimmingupdated this year
A self-hosted Stack Overflow-like application for Enterprise knowledge bases in Q&A and Article format. Includes RAG, MCP, and genAI (via external LLMs) support
MIT ★ 1 -
LLM agent that authors and runs integration tests for a complex 3-process C payments backend through a 15-tool MCP server, grounded in a generated knowledge base, with a controlled eval measuring whether the KB helps.
MIT ★ 1 -
obsidian-mcp-ultragithub.com/alch3mistdev/obsidian-mcp-ultraupdated this year
obsidian-mcp-ultra is a high-performance MCP (Model Context Protocol) bridge for Obsidian, exposing your vault as a structured, queryable knowledge graph for agentic workflows. It enables semantic retrieval, context injection, and bidirectional edits—turning your personal knowledge base into a live substrate for LLM-driven systems.
npm MIT ★ 1 -
Wolfram Alpha LLM APIgithub.com/henryhawke/wolfram-llm-mcpno update data
Given LLM's struggle with accurate mathematics and truth having the power of Wolfram Alpha is a huge improvement. Wolfram Alpha's LLM API computational knowledge engine through natural language queries to perform mathematical calculations, scientific computing, geographic information retrieval, and data analysis. Query facts about history, art, astronomy, and more with ease. Handle ambiguous queries with assumption-based clarifications for precise results.
smithery -
browser-mcpgithub.com/zzzhhhaaannnggg6/browser-mcpupdated this year
Vibe-coded browser-automation MCP server. Lets an LLM read, search, and traverse a private knowledge base via a persistent browser session — no vendor API key. Personal study project; the security questions surfaced while building it are turning into my undergraduate research interest.