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.
-
local-faiss-mcpgithub.com/nonatofabio/local_faiss_mcpupdated this year
MCP server with FAISS local vector database for RAG
pypi MIT -
local_faiss_mcpgithub.com/nonatofabio/local_faiss_mcpupdated this year
Local FAISS vector store as an MCP server – Agent Memory, drop-in local semantic search for Claude / Copilot / Agents.
pypi MIT ★ 36 -
Cortex-aigithub.com/CharonK652302/Cortex-aiupdated this year
Production RAG app — LangChain LCEL, LlamaIndex, Crew.ai multi-agent, FAISS, FastAPI, Docker, MLflow evaluation, GitHub Actions CI, MCP server — zero paid APIs
-
Ai_chatbotgithub.com/adityakumarprasad/Ai_chatbotupdated this year
AI Chat Workspace powered by Next.js and FastAPI. Features persistent PostgreSQL LangGraph checkpointers, multi-document RAG context searches via FAISS, and a custom GitHub MCP (Model Context Protocol) tool server using Gemini AI.
-
Local-first personal AGI GeoSentinel node — any OpenAI-compatible LLM plus dual-lane FAISS memory, offline voice, live global telemetry, sandboxed tools, a Discord bridge and an MCP server. No cloud required.
NOASSERTION ★ 5 -
consolidation-memorygithub.com/charliee1w/consolidation-memoryupdated this year
Local-first persistent memory for AI agents — store, recall, and consolidate knowledge across sessions using FAISS, SQLite, and any LLM. MCP server for coding agents and any MCP client.
pypi MIT ★ 8 -
Local-first memory layer for LLM apps and agents. Runs offline on Ollama, sentence-transformers and FAISS; OpenAI and Anthropic optional. Importance scoring, contradiction resolution, confidence-aware retrieval.
go Apache-2.0 ★ 50 -
mindcore-memory-mcpgithub.com/woshilaohei/mindcore-memory-mcpupdated this year
Production-hardened MCP memory server for AI agents: hybrid BM25+FAISS search, circuit breaker, SLO tracking, Prometheus metrics, BND boundary evaluation. Gives AI persistent long-term memory that survives across sessions.
pypi MIT ★ 1 -
Reference implementation for the Part II architecture paper (Zenodo 10.5281/zenodo.20374393) — dual-index FAISS memory, 42-opcode quaternionic VM, 5-phase retrieval, 36 tools, MCP server for Claude clients.
MIT ★ 2 -
Local code intelligence engine — three-tier FAISS + SQLite index with 10 MCP tools for semantic code search, blast radius analysis, and architectural investigation
-
An intelligent research assistant that searches, analyzes, and writes academic papers using a Retrieval-Augmented Generation (RAG) pipeline. Built with LangGraph, FAISS vector database,MCP and Google Gemini.
★ 1 -
pipecat-docs-mcpgithub.com/DTufail/pipecat-docs-mcpupdated this year
MCP server for Pipecat voice AI framework documentation. Search 6,936 chunks from 317 pages via Claude Desktop or Cursor. Hybrid BM25 + FAISS retrieval with cross-encoder reranking. 78.8% MRR, 93% Recall@5, 36ms avg latency.
-
A Model Context Protocol (MCP) server that enables AI assistants to interact with HubSpot CRM data, providing built-in vector storage and caching mechanisms help overcome HubSpot API limitations while improving response times.
MIT ★ 129 -
—
-
1c-conf-docgithub.com/gybson63/1c-conf-docupdated this year
MCP: semantic search over 1C:Enterprise config
MIT ★ 6 -
velociraggithub.com/haseebkhalid1507/velociragupdated this year
Lightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.
pypi MIT -
Replace Finder with an MCP server to search for your documents
MIT ★ 5 -
MCP-powered ecommerce customer support agent with MySQL and RAG
MIT ★ 1 -
memory-enginegithub.com/qq1009128320-dotcom/memory-engineupdated this year
四层记忆引擎 (Memory Engine) — 让 Agent 越用越聪明
MIT ★ 1 -
Source-grounded legal research across 5,936 German federal laws — retrieval, citations and reviewable next steps.
AGPL-3.0 ★ 2 -
consolidation-memorygithub.com/charliee1w/consolidation-memoryupdated this year
Trust-calibrated working memory for coding agents with provenance, drift awareness, and scoped sharing
pypi MIT -
Next-gen AI memory layer with hierarchical memory, importance scoring, and temporal retrieval
pypi Apache-2.0 -
vibescholargithub.com/kuff/vibescholarupdated this year
MCP server for academic research — Google Scholar search, Semantic Scholar enrichment, full-text PDF reading, and local corpus indexing
MIT ★ 1 -
VelociRAGgithub.com/HaseebKhalid1507/VelociRAGupdated this year
Lightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.
pypi MIT ★ 12 -
paper-workflowgithub.com/Minazuki02/paper-workflowupdated this year
Turn Claude Code into a research assistant. Search, ingest, retrieve, and analyze academic papers — zero CC source modification.
MIT ★ 1 -
Deterministic evidence about embedding spaces and vector indexes for agents: hubness, anisotropy, collapse, distance concentration, ANN recall, HNSW/IVF sweeps. CLI and MCP server.
pypi MIT -
📊 Automate job listing extraction from LinkedIn to streamline your research and recruitment efforts with efficient, bulk data collection.
★ 1 -
RegAIgithub.com/ananya-mh/RegAIupdated this year
AI-powered regulatory compliance engine. Automates gap analysis across GDPR, SOC 2, and HIPAA using multi-agent RAG pipelines, and generates audit-ready reports with citations.
-
MCP server for citation-finding research workflows: claim extraction, multi-source paper search (arXiv/Semantic Scholar/PubMed/OpenAlex), citation quality scoring, structured paper analysis.
MIT -
Local-first, LLM-agnostic memory system — hybrid retrieval (vector + lexical + graph), multi-signal ranking. Runs on 4GB RAM, CPU-only, no cloud.
MIT ★ 18 -
Deterministic evidence about embedding spaces and vector indexes for agents: hubness, anisotropy, collapse, distance concentration, ANN recall, HNSW/IVF sweeps. CLI + MCP server.
MIT ★ 1 -
OpenScout is a Perplexity-inspired answer engine that turns a single question into a grounded, cited response. It combines web search, retrieval, reranking, and LLM synthesis in a lightweight Streamlit Application
MIT ★ 1 -
A MCP server that enables Claude to discover and call any API endpoint through semantic search. Intelligently chunks OpenAPI specifications to handle large API documentation, with built-in request execution capabilities. Perfect for integrating private APIs with Claude Desktop.
go MIT ★ 82 -
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.
-
AI shopping concierge: natural-language product search where an LLM reads the limits and Python enforces them, BGE semantic + keyword retrieval, personalized ranking and fact-checked answers. Streamlit demo, REST API, chat widget, MCP server.
-
A multi-agent NLP system that analyzes, summarizes, and compares insurance policy documents. It enables intelligent document understanding, semantic search, and comparative analysis between Tunisian and international insurance standards
-
USPTO patent creation system with MCP server + Claude Code plugin. Hybrid RAG search over MPEP/USC/CFR, BigQuery access to 76M+ patents, automated 35 USC 112 compliance checks, prior art search, diagram generation. GPU-accelerated with skills and autonomous agents.
MIT ★ 211