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.
-
mcp-arango-mindgithub.com/woolkingx/mcp-arango-mindupdated this year
Schema-driven ArangoDB MCP server with OpenAPI search/exec, AQL templates, and knowledge-atlas projections.
MIT -
Local-first, spec-driven SDLC workbench with governance gates, knowledge graphs, and MCP for AI coding agents.
pypi NOASSERTION ★ 141 -
MCP server for AI coding agents — persistent engineering memory, knowledge compounding, and spec-driven development workflows. Part of TRW Framework.
pypi NOASSERTION -
aidd-kosgithub.com/spikestudio/aidd-kosupdated this year
Agentic Knowledge OS — LightRAG knowledge graph + MCP server for AI-driven development
pypi MIT -
Read-only MCP server for spec-driven development: estate contract lookup, knowledge-layer checks, and spec inventory over a local repo, plus the toolkit's spec-driven commands served as MCP prompts.
npm MIT -
knowledge-mcp-servergithub.com/achellesheel/knowledge-mcp-serverupdated this year
Local MCP server + CLI turning PDFs/notes into a semantic knowledge base — FAISS + sentence-transformers, hybrid BM25/dense search, cross-encoder reranking, eval-driven.
MIT -
Centralized, AI-driven, Harness-agnostic knowledge store: a governed knowledge vault exposed over MCP, with correctness enforced at write time.
MIT -
A template for building structured, self-healing, agent-accessible knowledge bases. Zero dependencies. Git-native. Ontology-driven. Multi-output.
MIT ★ 8 -
AI-driven knowledge training platform with pluggable schedulers, Codex Skill integration, and optional Anki/FSRS support.
MIT ★ 129 -
Config-schema-driven vector knowledge base: LanceDB storage, pluggable embedding/reranker/graph backends, CLI + HTTP REST + MCP (stdio & streamable HTTP)
cargo MIT OR Apache-2.0 -
Business Central Knowledge Base MCP Server - Persona-driven workflow orchestration and intelligent BC knowledge discovery
npm 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 -
Ontology-driven knowledge graph of US defense procurement: USASpending ETL, BFO/CCO ontology on Jena Fuseki, Claude-powered MCP server
MIT -
Model Context Protocol (MCP) server for spec-driven development: read-only spec inventory, knowledge-layer checks, and cross-service contract lookup for Claude, Cursor, VS Code and any MCP client.
npm MIT -
AI-Prompt-Guide-MCPgithub.com/Blakeem/AI-Prompt-Guide-MCPupdated this year
Deprecated. MCP server and Claude Code plugin with task driven agent orchestration workflows, guides, markdown knowledge graphs, with intelligent context injection.
MIT ★ 5 -
Config-driven code knowledge graph for Vue projects — tree-sitter AST parsing, Living Wiki, MCP server for AI agents, Sigma.js visualization
npm -
@code-sense/coregithub.com/atbeta/code-senseupdated this year
Config-driven code knowledge graph for Vue projects — tree-sitter AST parsing, Living Wiki, MCP server for AI agents, Sigma.js visualization
npm MIT -
pargithub.com/latentfidelity/parupdated this year
Persistent Agent Runtime — self-hosted cognitive runtime for AI coding agents: semantic memory, knowledge graph, agent coordination, event-driven workflows, and autonomous self-maintenance via MCP
MIT ★ 9 -
AST-driven Neo4j knowledge graph of your codebase, exposed to Claude Code via MCP. Map your monorepo once; let the agent query it instead of re-reading files.
npm MIT -
wiki-compilergithub.com/Ray0907/wiki-compilerupdated this year
Compile web sources into a structured, growing Obsidian knowledge base. CLI + MCP server, schema-driven, local-first.
-
Open-source engine for AI-native sales systems — ontology-driven data, one permission kernel, change-set provenance, and native MCP (2026-07-28). Business logic is loaded from pluggable, signed knowledge packs.
Apache-2.0 -
korvagithub.com/AlcanDev/korvaupdated this year
The OS for AI-driven engineering teams. Persistent memory + architecture guardrails + curated knowledge scrolls for Claude Code, Cursor, GitHub Copilot, OpenCode, VS Code MCP, Codex, Gemini, Windsurf. Local-first, privacy-preserving, MCP-native. Open source.
go MIT -
lore-ossgithub.com/eliasem-ka/lore-ossupdated this year
Agent-driven, human-in-the-loop knowledge base: AI agents extract business rules from code via MCP, reviewers approve/reject in a web UI, and rejected rules feed back to refine — a converging loop.
AGPL-3.0 -
ex-Plain-mcpgithub.com/krystianslowik/ex-Plain-mcpupdated this year
Community-driven MCP server for Plain.com customer support. Gives AI agents full access to threads, customers, and knowledge: search, read, and take action.
-
Repository knowledge for coding agents: task-driven retrieval, capability cards, and commit-pinned evidence via MCP and Skills.
MIT -
Enterprise knowledge assistant with routed RAG, LangGraph workflows, MCP tools, verified delivery, evaluation, and API-driven HITL writes.
-
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 -
Turn any codebase into a searchable knowledge base for AI coding assistants. Config-driven RAG pipeline + MCP server with hybrid semantic/keyword search.
NOASSERTION ★ 1 -
A type system, state validator, and safety firewall between AI coding assistants and physical instruments — schema-driven, MCP-native, zero hardware knowledge in the engine.
MIT ★ 1 -
OpenCode plugin + MCP server that saves 98% of your context window. Sandboxed code execution, FTS5 knowledge base, and intent-driven search.
npm MIT -
Context-saving MCP extension for Pi Coding Agent with sandboxed code execution, FTS5 knowledge base, and intent-driven search.
npm Elastic-2.0 -
MCP server that gives AI coding agents persistent, structured repository knowledge — incremental tree-sitter indexing, dependency & call graphs, semantic summaries, hash-driven cache. C++23.
MIT -
msxai-harnessgithub.com/vdom-1/msxai-harnessupdated this year
AI-driven MSX development and operations harness, featuring documentation organized via the Open Knowledge Format (OKF), automated build workflows, and direct agent-to-emulator communication via MCP to execute complex tasks.
MIT ★ 1 -
MCP server that lets AI agents query Refined Element's Kentico-managed knowledge pack — Xperience by Kentico upgrades, GEO, AI-driven development, Sentinel, and CMS architecture — including one L402-paid premium endpoint.
npm MIT -
MCP plugin that saves 98% of your context window. Works with Claude Code, Gemini CLI, VS Code Copilot, OpenCode, and Codex CLI. Sandboxed code execution, FTS5 knowledge base, and intent-driven search.
npm Elastic-2.0 -
MCP plugin that saves 98% of your context window. Works with Claude Code, Gemini CLI, VS Code Copilot, OpenCode, and Codex CLI. Sandboxed code execution, FTS5 knowledge base, and intent-driven search.
npm Elastic-2.0 -
Self-hosted multi-agent AI infrastructure: an MCP server exposing 48 tools for agent-driven infrastructure management, a multi-provider LLM gateway over commercial and self-hosted models, and a PostgreSQL knowledge graph with vector search. Architecture notes; source is private.
-
@2kw/ai-mcp-serveractive
MCP server for 2kw.ai — EU-hosted AI platform: OpenAI-compatible LLM gateway, schema-driven document extraction, transcription, agents with a knowledge base, and cost observability. 199 tools for Claude Code, Cursor, and Windsurf.
npm SEE LICENSE IN LICENSE -
MCP server that lets AI agents query Refined Element's Xperience by Kentico-managed knowledge pack — Kentico upgrades, GEO (generative engine optimization), AI-driven development, Sentinel, and CMS architecture — including L402-paid premium items over Lightning. The .NET delivery surface; a TypeScript/npm sibling also exists.
nuget MIT -
Ontology service layer for AI agents: discover T-Box concepts, query grounded A-Box evidence, and invoke permissioned actions over MCP and REST.
-
Transport-neutral domain engine for Okto Pulse: governed SDLC workflows, knowledge graph contracts, and 281 MCP tools.
pypi NOASSERTION ★ 7 -
@alexdx/chronicle-mcpgithub.com/alexdx2/chronicleupdated this year
Chronicle MCP — self-learning knowledge graph for code analysis. MCP server for Claude Code.
npm MIT -
NinFenz · 规范驱动的文档生成工坊:把「想法」变成可校验、可复用的结构化文档(CLI / MCP / 桌面 / 9 种语言引擎)
npm MIT ★ 1 -
Context layer for AI agents in vertical SaaS: domain events in, a bitemporal context graph per end-customer out, five MCP tools for every agent.
pypi Apache-2.0 ★ 15 -
Autonomous development pipeline — aa: · ag: · audit: · AST graph · Harness · Specs · Impact analysis · Decision trail · Metrics · MCP server. Works with Cursor and Claude Code.
npm MIT -
Open-source GraphRAG domain knowledge layer: LLMs continuously distill scattered skill docs into a queryable, evolvable, human-editable two-layer knowledge graph — versioned, hot-swapped and rolled back via a GitOps pipeline like software releases, and served to AI agents over MCP. RAG, but with relational structure.
MIT ★ 113 -
Agent-first content publishing engine. Config-driven, MCP-native, forkable.
★ 1 -
Evidence-driven RAG. Hybrid BM25 + vector retrieval with citations you can re-verify. Local-first, zero API keys, MCP-native.
Apache-2.0 -
nbraggithub.com/ydf0509/nbragupdated this year
Agentic RAG MCP Server — 13 retrieval/read tools plus workflow help for AI-driven multi-round retrieval over any text
pypi MIT -
agent-wiki-kitgithub.com/AvalancheAI-labs/agent-wiki-kitupdated this year
wikikit — one zero-dependency engine for every LLM wiki: lint (contracts, links, freshness), publish (llms.txt/HTML), serve over MCP, agent-driven ingest
MIT -
BC Code Intelligence MCP Server - Complete Specialist Bundle with AI-driven expert consultation, seamless handoffs, and context-preserving workflows
npm MIT -
BC Code Intelligence MCP Server - Complete Specialist Bundle with AI-driven expert consultation, seamless handoffs, and context-preserving workflows
npm MIT -
Hoofygithub.com/HendryAvila/Hoofyupdated this year
Hoofy — AI development companion MCP server. Persistent memory, spec-driven development, adaptive change pipeline, Clarity Gate. 32 tools, single Go binary, zero deps.
go MIT ★ 16 -
redraftgithub.com/KaelinGraf/redraftupdated this year
Typed, versioned design records for engineering projects — decisions, rationale, and the roads not taken, kept as plain Markdown and driven by your agent over MCP.
Apache-2.0 ★ 3 -
🎓 LEAP Framework — a state-driven agentic tutoring runtime for AI agents, exposed over MCP. Server-side State Guard, evidence-based mastery, FSRS retention.
MIT ★ 1 -
A clonable, self-contained starter for a governed Obsidian vault driven by an MCP server: domain ontology, rules registry, authority levels, and a writing-preflight gate.
MIT -
jv-obsidian-assistantgithub.com/janvrsinsky/jv-obsidian-assistantupdated this year
Portfolio extract of a persona-driven AI assistant over an Obsidian Markdown vault through a typed MCP filesystem core. The private original runs daily; this sanitized cut reads before it answers, routes every write to its owning note, and a standard-library self-test verifies those claims in CI.
MIT ★ 1