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.
-
docs-rag-mcpgithub.com/shrish346/docs-rag-mcpupdated this year
MCP server exposing TF-IDF RAG over a markdown corpus as tools + resources
-
Knowledge Center MCP-style tools over teaching lesson notes (offline TF-IDF)
MIT -
hh-mcp-servergithub.com/Vadtop/hh-mcp-serverupdated this year
hh.ru MCP server: vacancy search and auto-apply via Playwright, TF-IDF scoring, 19 tools, 41 tests
MIT ★ 1 -
mcp-knowledge-basegithub.com/zavora-ai/mcp-knowledge-baseupdated this year
Knowledge Base MCP Server — articles, policies, known issues, TF-IDF search, feedback loops, gap detection, and source-grounded answers
cargo Apache-2.0 -
🔌 Exposes Keyword extraction over MCP — TF-IDF, RAKE, YAKE, semantic relevance, search volume estimation. MIT.
pypi MIT -
knowledge-base-mcpgithub.com/dyyz1993/knowledge-base-mcpupdated this year
Knowledge Base MCP service with 3-layer search (text/TF-IDF/embedding) and Web UI
npm -
MCP server: ask a public GitHub repo questions, get line-cited answers. TF-IDF retrieval, zero-cost by default, optional LLM synthesis.
MIT -
Cascade — an AI-native operations layer for knowledge work. Hook runtime, TF-IDF knowledge search, domain-aware agent routing, MCP intelligence server.
MIT -
Cross-session memory and recall for AI agents — git-synced knowledge base, hybrid semantic+TF-IDF search, auto-distillation with secrets scrubbing
npm MIT ★ 19 -
跨会话跨项目本地记忆 MCP server — flexsearch BM25 + TF-IDF 三路混合检索,双时钟事实管理,自动 Hook 链路。零 native 依赖,纯 Markdown vault。
npm MIT -
⚡ ChronoFact: 4-Pillar Epistemic AI Backbone. Real-time temporal cutoff calibration, active NLI claim verifier, zero-pollution memory, and mcplex TF-IDF cost optimizer.
MIT ★ 2 -
CogniVaultgithub.com/gitstq/CogniVaultupdated this year
🧠 CogniVault - Lightweight AI Agent Semantic Memory Engine | 轻量级AI Agent语义记忆引擎 - Zero Dependencies, TF-IDF+BM25 Hybrid Search, Memory Lifecycle, Knowledge Graph, MCP Server
MIT -
RAG engine for whole websites: async multi-page scraping with JS rendering, hybrid semantic + TF-IDF ranking on FAISS, LLM answers, and an MCP server so AI agents can query it.
-
Semantic search over RSS/Atom feeds for AI agents — a single-file MCP server with TF-IDF ranking, trending topics, markdown digests, and SSRF-safe fetching.
pypi MIT -
nexus-mcp-agentgithub.com/anomalyco/nexus-mcpupdated this year
Agentic OS MCP Server — 150+ tools with on-demand loading (26 core), Streamable HTTP transport, background task engine, browser automation, TF-IDF semantic memory, multi-agent orchestration. Zero API keys.
npm MIT -
porta-rag-mcpgithub.com/Ira-Korshunova/porta-rag-mcpupdated this year
RAG knowledge base как MCP-tools: поиск по документам для любого AI-клиента (Claude/Cursor/ChatGPT). FastMCP-обёртка над RAG-движком, оптимизация токенов (retrieval без LLM vs полный RAG). Demo-бэкенд TF-IDF + интерфейс для production FAISS+BM25+rerank.
-
MCP server that gives Claude self-updating access to a local document directory. TF-IDF search, live file watching, PDF/DOCX/MD support. Built for legal workflows, works with any documents.
MIT -
Headless semantic MCP server for Obsidian, Logseq, Dendron & any markdown vault. AST-based surgical editing, hybrid vector + TF-IDF search, zero-setup local embeddings — no app or plugins required. Stdio & SSE transport, Docker-ready.
npm MIT ★ 12 -
AI-Act-Evidence-Deskgithub.com/MoSaleh47/AI-Act-Evidence-Deskupdated this year
Agentic RAG assistant that turns an AI use case into a source-grounded EU AI Act evidence map. Hybrid BM25/TF-IDF retrieval with rank fusion, three-pass self-consistency synthesis, MCP server, RAGAS evaluation and prompt-injection tests.
-
codexraygithub.com/NeuralRays/codexrayupdated this year
X-ray vision for your codebase — semantic knowledge graph & MCP server with 16 tools that saves AI coding agents 30%+ tokens. TF-IDF search, call graphs, impact analysis, dead code detection. Works with Claude Code, Cursor & Windsurf.
npm MIT ★ 8 -
Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem with 600x lower cost.
npm MIT ★ 68 -
Occupation classification and job-title normalization for the O*NET-SOC taxonomy. A fine-tuned retrieve-and-rerank model maps job titles, resumes, postings and skill lists to ranked SOC codes with calibrated confidence. 51% top-1 vs 21% TF-IDF. Python, CLI, REST API, MCP server. Runs locally.
pypi MIT ★ 2 -
Fully local MCP retrieval tool for coding agents. 161M encoder, ~1s per tool call, no API, no LLM in the query path. No file reads: line numbers, callers, callees and exact call sites, packed to a token budget. 2-4x the file coverage of BM25 and TF-IDF on SWE-Explore, and tops the paper's own sub-1B code model on CORE-Bench.
MIT ★ 5 -
mcp-external-memorygithub.com/daedalus/mcp-external-memoryupdated this year
—
pypi MIT -
Agentic Steam game recommender with an MCP server, LLM agents and a FastAPI backend.
-
@theihtisham/contextforgegithub.com/theihtisham/contextforgeupdated this year
The MCP server that makes AI coding agents actually understand your codebase
npm MIT -
@theihtisham/mcp-context-forgegithub.com/theihtisham/mcp-context-forgeupdated this year
The MCP server that makes AI coding agents actually understand your codebase
npm MIT -
Vector-Knowledge-Basegithub.com/i3T4AN/Vector-Knowledge-Baseupdated this year
A semantic search engine that transforms your documents into an intelligent, searchable knowledge base using vector embeddings and AI
MIT ★ 10 -
collective-memory-mcpgithub.com/YOUR_USERNAME/collective-memory-mcpupdated this year
A smart, three-tier memory system for AI agents with context-efficient search and auto-classification (MCP Server)
npm MIT