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 MCP server (stdio) that extracts live pages and multi-step flows into compact Semantic JSON with Playwright-native locators, observed behavior (navigations, requests) and snapshot diffs, for consistent AI-generated Playwright tests.
npm MIT -
arxiv-mcp-searchgithub.com/hjh-12138/arxiv-mcp-serverupdated this year
MCP server for arXiv paper search with semantic search, citation enrichment, and PDF extraction
pypi MIT -
mcp-fact-findergithub.com/bobmatnyc/mcp-fact-finderupdated this year
Semantic fact indexer over markdown knowledge bases — extracts atomic facts, entities, and authority scores, then exposes search via MCP
pypi Other/Proprietary License -
@iflow-mcp/renefichtmueller-papercortexupdated this year
Self-hosted AI intelligence layer for Paperless-ngx with semantic search, receipt extraction, and MCP Server integration
npm MIT -
Kappa Graph — κ(G). A semantic knowledge graph where knowledge has weight. Extracts concepts, measures grounding strength, preserves disagreement, traces everything to source.
go Apache-2.0 ★ 131 -
DeepFetchgithub.com/vinay9986/DeepFetchupdated this year
Semantic web search MCP server with Kagi, Scrapfly, PDF extraction, and local ONNX reranking for Claude Desktop, Gemini CLI, and Codex.
Apache-2.0 -
MCP server for document management — multi-format extraction, semantic search, OCR, hash-based deduplication
Apache-2.0 ★ 1 -
semantic-kernel-agentgithub.com/AnithaKarre/semantic-kernel-agentupdated this year
A Figma design-to-code agent built on Microsoft Semantic Kernel — extracts design tokens (text, colors, layout) from Figma via a custom MCP server and generates JSX-ready code. Supports multi-provider LLM routing (Azure OpenAI, OpenAI, Ollama, Gemini, HuggingFace) and modular prompt templates.
-
MCP server exposing direct arXiv/Crossref/Semantic Scholar/Tavily search and PDF full-text extraction as tools.
MIT -
doc-agentgithub.com/prosdevlab/doc-agentupdated this year
Document extraction and semantic search CLI with MCP integration. Extract structured data from invoices, receipts, and bank statements using Vision AI.
MIT -
Extract any website's complete design system with one command. DTCG tokens, semantic+primitive+composite, MCP server for Claude Code/Cursor/Windsurf, multi-platform emitters (iOS SwiftUI, Android Compose, Flutter, WordPress), Tailwind v4, Figma variables, shadcn/ui, CSS health audit, WCAG remediation, Chrome extension. MIT, Playwright, Node 20+.
npm MIT ★ 5,107 -
CrawlEyes - Web Scraping & Search Toolkit for AI Agents. Full-text extraction + robust search + semantic reranking + MCP server. Zero API-key fallback, China-friendly.
MIT ★ 2 -
crawleyesactive
CrawlEyes - Web Scraping & Search Toolkit for AI Agents. Full-text extraction + robust search + semantic reranking + MCP server. Zero API-key fallback, China-friendly.
pypi MIT -
aethenegithub.com/Nuro-Labs/aetheneupdated this year
The Open-Source AI Memory Layer: store content, extract atomic memories, search semantically and recall context for AI agents. Self-hostable with an MCP server.
MIT ★ 6 -
Post-Cortex provides durable memory infrastructure with automatic knowledge graph construction, intelligent entity extraction, and semantic search powered by local transformer models.
MIT ★ 20 -
ResearchMcpgithub.com/Adityay009/ResearchMcpupdated this year
Agentic research assistant with a custom MCP server (9 tools) and a LangGraph agent that autonomously searches arXiv, extracts papers, and builds a semantic research library.
-
UltraMemorygithub.com/win4r/UltraMemoryupdated this year
Universal AI Agent Long-Term Memory Engine — Hybrid Vector+BM25, cross-encoder reranking, Weibull decay, LLM smart extraction, semantic dedup, tiered content. Zero-ops LanceDB backend.
★ 7 -
MCP server for bgustscraper — semantic scraping, document extraction and legal compliance (BGUST ecosystem).
cargo non-standard -
Rust MCP web-intelligence server — fetch, extract, crawl, monitor, interact, PDF, semantic search
MIT ★ 2 -
Extract Microsoft Fabric semantic model metadata. AI-ready exports for LangChain, OpenAI, Semantic Kernel, AutoGen, and custom plugins. Multi-provider LLM enrichment, MCP server, and cross-model governance.
pypi MIT ★ 1 -
MCP server for Power BI with PBIX analysis, semantic model extraction, report export, and cloud operations.
npm MIT ★ 1 -
MCP server for academic research — 25+ tools for OpenAlex, CrossRef, ArXiv, SciELO, Semantic Scholar, Unpaywall, SJR/Qualis, Citation Verification, Bibliometrics, PDF Extraction
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 -
Semantic browser automation MCP server — 24 tools for AI agents, label-based resolution, structured extraction, CDP access
MIT ★ 1 -
🔌 Exposes Keyword extraction over MCP — TF-IDF, RAKE, YAKE, semantic relevance, search volume estimation. MIT.
pypi MIT -
barnacle-searchgithub.com/zjs81/barnacle-searchupdated this year
A local MCP server that attaches to your codebase and gives Claude semantic search, symbol extraction, and auto-reindexing
-
SakuttoWorksgithub.com/SakuttoWorks/SakuttoWorksupdated this year
Agent-Commerce-OS: Secure MCP infrastructure for RAG-optimized web data normalization and semantic extraction.
MIT -
Cognitive memory system for Claude Code: episodic storage, semantic extraction, knowledge graph, and dream-state consolidation. TypeScript, MCP server, local-first.
npm MIT ★ 1 -
rigithub.com/sazardev/riupdated this year
CLI engine & MCP server for semantic code architecture extraction, validation, and visualization. Optimized for AI agent context efficiency.
-
Local long-term memory CLI for AI agents — semantic search, async fact extraction, built-in MCP stdio server (8 tools). 本地长期记忆服务,支持 MCP 即插即用。
Apache-2.0 -
MCP server for Telegram with semantic search, AI-powered knowledge extraction, Bot API/MTProto support, human-in-the-loop actions, and PostgreSQL + pgvector persistence.
NOASSERTION -
Local-first semantic search MCP over Fathom meeting recordings. Extract, embed, and query your full meeting history — no cloud AI required.
MIT -
uuparsergithub.com/fuadarradhi/uuparserupdated this year
UUParser – Qanun Aceh MCP Server provides AI-ready access to Aceh's legal regulations through the Model Context Protocol (MCP), featuring structured documents, article-level parsing, metadata extraction, and semantic search.
-
looking-glass-mcpgithub.com/sahib-sawhney-wh/lookingglassupdated this year
AI-native browser for agents — semantic change detection, self-healing interactions, structured extraction, credential vault, and enterprise Azure deployment
npm MIT -
cwm.roslynnavigatorgithub.com/codewithmukesh/dotnet-claude-kitupdated this year
A Model Context Protocol (MCP) server that gives AI coding assistants semantic understanding of .NET codebases via Roslyn. 20 read-only tools for symbol navigation, reference finding, type hierarchy, dependency graphs, anti-pattern detection, dead code analysis, diagnostics, file outlines, symbol source extraction, NuGet package inventory, endpoint maps, and DI registration analysis — all returning token-optimized responses. Part of the dotnet-claude-kit ecosystem.
nuget MIT -
marketlens-llm-mcpgithub.com/MarketLens-AI-Platform/marketlens-llm-mcpupdated this year
LLM-powered semantic enrichment service. DeepSeek-driven feature extraction (sentiment, categorization, attributes) behind a secure Model Context Protocol (MCP) server. LangChain pipeline for transforming raw product text into ML-ready vectors.
MIT -
Shared, persistent memory store for AI agents — one SQLite file, one Bun process, REST + MCP + web UI. Keyword FTS5 + optional semantic search, LLM extraction, configurable LLM settings. v2.0.0.
MIT -
pdf-rag-mcpgithub.com/MBaranekTech/pdf-rag-mcpupdated this year
MCP server for RAG over messy PDFs — semantic search, OCR, table extraction. Works with Claude Desktop, Claude Code, Cursor, and any MCP client.
MIT -
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 -
dao-searxng-mcpgithub.com/leiverkus/dao-searxng-mcpupdated this year
MCP server that turns a local SearXNG instance into citation-aware web search for AI agents — Readability extraction, MiniLM semantic rerank, inline-clickable markdown citations.
MIT ★ 2 -
An enhanced MCP (Model Context Protocol) server for intelligent memory and task management, designed for AI assistants and development workflows. Features semantic search, automatic task extraction, knowledge graphs, and comprehensive project management.
pypi MIT ★ 33 -
Self-hosted MCP memory server. Each project gets isolated memory with LLM fact extraction, deduplication and semantic search. Works with Claude Code, Codex, Copilot, Cursor and any MCP client.
AGPL-3.0 ★ 7 -
TalentMind An intelligent recruitment platform leveraging the Model Context Protocol architecture to enable context-aware AI matching between candidate profiles and job requirements. Built with React, FastAPI, and MongoDB, featuring CV processing, job extraction, and advanced LLM orchestration for semantic compatibility assessments.
-
Persistent semantic memory for Claude Cowork. Extracts beliefs, insights, and research from every session into a local database Claude queries in real time. Nightly research scouting, automated belief verification, and MCP-based retrieval. Built for Cowork — not Claude Code.
MIT -
MCP server with 40 tools for web design analysis — layout extraction, motion detection, quality scoring, accessibility audit, Core Web Vitals, design comparison, and semantic search via Playwright, pgvector, ONNX Runtime, and Ollama.
npm AGPL-3.0 ★ 2 -
AI document intelligence for Paperless-ngx — semantic search, receipt extraction, and one-click DATEV export with a built-in bilingual web UI. 100% local via Ollama, ships as an MCP server for Claude Code.
MIT ★ 34 -
AuditFlow is text & voice chat application for auditors to extract insights from financial documents like trial balances and general ledgers. Built with an MCP Server using Supabase (PostgreSQL) and SQLAlchemy ORM, it uses Weaviate Vector Store for hybrid search combining BM25, metadata, and semantic search for data retrieval, integrated with n8n.
-
Semantic Java refactoring for AI coding agents. Rename, move, extract, inline, pull up/push down and more — backed by Eclipse JDT, the same engine as IntelliJ and Eclipse. The IDE your coding agent never had.
Apache-2.0 ★ 3 -
agent-browsergithub.com/atreasureboy/agent-browserupdated this year
Agent-readable semantic browser layer for AI agents — token-efficient web understanding, semantic snapshots, persistent sessions, and MCP/CLI/Python APIs.
MIT ★ 1 -
recipe-toolsgithub.com/lka/recipe-toolsupdated this year
MCP server for extracting recipes from PDFs or jpegs into structured HTML using OCR and LLM-assisted interpretation.
MIT -
mcp-browsergithub.com/bobmatnyc/mcp-browserupdated this year
MCP server for browser automation with Chrome extension. 5 MCP tools for DOM interaction, console capture, content extraction, screenshots. Optimized for Claude Code and other agentic coding tools.
MIT ★ 2 -
Document image retrieval via MCP or API for agentic systems using semantic embeddings, YOLO, and VLM classification.
NOASSERTION ★ 4 -
Bulkgrid - Better AI Answers From Sources You Trust
★ 5 -
taladb-pipelinegithub.com/taladb/taladb-pipelineupdated this year
Local-first RAG toolkit for JavaScript — extract, embed, and search documents entirely on-device. EPUB, DOCX, Markdown, HTML. MCP server included.
Apache-2.0 -
Turn your documents into agent memory. MCP server with hybrid semantic + keyword search over emails, PDFs, notes, and past conversations. Works with Claude, ChatGPT, Cursor, and any MCP client.
MIT ★ 6 -
An open-source, local-first Model Context Protocol (MCP) server for Named Entity Extraction, Wikidata Disambiguation, sameAs Schema Linking, and Knowledge Graph Triple Construction
pypi MIT -
An open-source, local-first Model Context Protocol (MCP) server for Semantic Keyword Clustering, Search Intent Classification, Cannibalization Detection, and Topical Authority Mapping.
pypi MIT -
MCP server exposing TypeSafe Jev as purpose-built judgment tools: verify claims, screen for injection, find, rerank, classify, decide, compare passages, extract fields, review patches, and gate completion claims, each with typed probabilities.
npm MIT -
ontomicsgithub.com/EtienneChollet/ontomicsupdated this year
Extract domain knowledge from codebases to reduce LLM token consumption by 20x and time in agentic search by 10x — gathers and makes concepts, naming conventions, and vocabulary queryable via MCP.
npm MIT ★ 44