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.
-
@mseep/figma-mcp-chunkedstale
Figma MCP server with chunking and pagination
npm ISC -
Split Markdown into chunks by heading. Each chunk keeps its heading path and line numbers. CLI and MCP server. Runs locally.
pypi MIT -
Test that a streaming redactor or LLM guardrail cannot leak a secret split across chunks.
pypi Apache-2.0 -
Split Markdown into RAG chunks by heading. Keeps heading path and line numbers. Local Python CLI and MCP server.
MIT -
MCP server for reading Excel files with automatic chunking and pagination support
npm MIT -
MCP server for universal text extraction, keyword extraction, language detection, and text chunking for RAG pipelines
npm MIT -
URL → RAG-ready Markdown in one API call: heading-aligned chunks, embeddings, change-aware re-indexing, docs crawler + llms.txt, MCP server. Free tier.
-
MCP server for editing R Markdown (.rmd) documents with 24 cell-level tools: create, read, search and restructure cells, read and set knitr chunk options and YAML frontmatter keys, and run chunks on a live Jupyter kernel (R via IRkernel; Python, Julia via installed kernels). Built on PyYAML and jupyter_client.
MIT -
@iflow-mcp/fast-filesystem-mcpgithub.com/efforthye/fast-filesystem-mcpupdated this year
Fast Filesystem MCP Server - Advanced file operations with Auto-Chunking, Sequential Reading, complex file operations (copy, move, delete, batch, compress), optimized for Claude Desktop
npm Apache-2.0 -
This cli tool/Model Context Protocol (MCP) server chunks source code files using LangChain's RecursiveCharacterTextSplitter and stores the resulting chunks in a ChromaDB vector database, including line range metadata for each chunk.
MIT ★ 2 -
retrieval-lensgithub.com/Vbj1808/retrieval-lensupdated this year
MCP server that audits RAG retrieval - logs what chunks the model saw before any answer was generated
MIT ★ 2 -
MCP server for Web2MD: web pages to clean Markdown and token-bounded RAG chunks (via RapidAPI)
MIT -
MCP server for semantic code search — AST-aware chunking, hybrid dense+sparse search, 160+ languages
Apache-2.0 ★ 1 -
Turns web pages into decision-ready state: dates as dates, numbers computed, chunks sized for models that classify instead of write.
npm MIT -
PDF Liberation MCP Server - Break large PDFs into digestible chunks for Claude
AGPL-3.0 -
oboyugithub.com/sonesuke/oboyuupdated this year
Self-hosted MCP Japanese text indexing & search—chunking+embeddings with BM25×vector rerank
MIT ★ 3 -
webcontext-aigithub.com/sumeeth-24/webscrapper-aiupdated this year
Turn any web content into clean AI-ready context — with crawling, chunking, semantic search, and MCP tools
npm MIT -
mimirsgithub.com/thewinci/mimirsupdated this year
Persistent project memory for AI coding agents — semantic search, AST-aware chunking, dependency graphs, and conversation history
npm Apache-2.0 -
@smallthinkingmachines/semantic-code-mcpgithub.com/smallthinkingmachines/semantic-code-mcpupdated this year
MCP server for semantic code search using AST-aware chunking and vector embeddings
npm MIT -
sraggithub.com/wrxck/sragactive
Semantic code search and RAG system written in Rust with tree-sitter chunking, MCP server for IDE integration, prompt injection detection, and secret redaction
GPL-3.0 ★ 21 -
trawlgithub.com/bbulb/trawlupdated this year
Selective web content extraction for AI agents — URL + query returns only the chunks that matter (Python library + MCP server)
MIT ★ 3 -
Local MCP bridge for Maya — mcp-socket family, wire-compatible with blender-mcp. Physical screen capture, undo-chunked execution.
GPL-3.0 ★ 1 -
pluckgithub.com/hunhee98/pluckupdated this year
MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup
MIT ★ 43 -
kaos-astgithub.com/ulolol/kaos-astupdated this year
High-precision code context provider for AI agents. Bridges code_ast parsing with cocoindex-code for semantic chunking and local vector embeddings
MIT -
Local MCP code search that cuts AI agent tokens: AST chunks, CPU reranking and a dependency impact graph. -63.9% tokens measured.
MIT ★ 1 -
MCP server for semantic code search with AST-aware chunking, incremental indexing, and real-time monitoring. --- idk if it works or, moreover, is actually helpful. But it is cool.
★ 3 -
Chomper - Chomp through any document. MCP server for parsing 36+ file formats with semantic chunking & TOON token optimization for Claude and AI systems.
MIT ★ 1 -
MCP server that gives an AI assistant deterministic document tooling: PDF/text reading, chunking, JSON Schema validation, structured output — path-confined, fully tested
MIT -
descrygithub.com/jKiler/descryupdated this year
Local hybrid (vector + BM25) code search for AI coding agents — AST chunking, MiniLM embeddings on ONNX, Go call graph, MCP server. No external services.
Apache-2.0 ★ 1 -
MCP Documentation Server - Bridge the AI Knowledge Gap. ✨ Features: Document management • Gemini integration • AI-powered semantic search • File uploads • Smart chunking • Multilingual support • Zero-setup 🎯 Perfect for: New frameworks • API docs • Internal guides
MIT ★ 346 -
Turn any website into a quality-scored LLM fine-tuning dataset: crawl, chunk, generate Q&A, score, export to JSONL/Parquet/HF Hub. CLI plus MCP server.
MIT ★ 2 -
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.
-
anchorgithub.com/myrddian/anchorupdated this year
Source-grounded chunk validation as a primitive. Spring Boot service exposing two interfaces (LLM-to-LLM and human-facing) over the same hierarchical document model.
Apache-2.0 ★ 3 -
Semantic code search MCP server: Tree-sitter AST chunking + voyage-code-3 embeddings + hybrid retrieval (sqlite-vec + FTS5 + RRF) + Voyage rerank-2.5 + call graph expansion
MIT ★ 2 -
@iflow-mcp/softerist-heuristic-mcpgithub.com/softerist/heuristic-mcpupdated this year
An enhanced MCP server providing intelligent semantic code search with find-similar-code, recency ranking, and improved chunking. Fork of smart-coding-mcp.
npm MIT -
ftp-mcpgithub.com/kynlos/ftp-mcpupdated this year
Enterprise-grade MCP server providing heavily optimized FTP/SFTP operations with smart sync, patch/chunk streaming, caching, and explicit read-only security mappings for AI code assistants.
npm MIT -
Engramgithub.com/Artemarius/Engramupdated this year
GPU-accelerated local semantic code index for Claude Code. CUDA-powered embeddings, HNSW vector search, tree-sitter AST chunking, MCP server — sub-3ms queries, fully on your machine.
★ 1 -
Multi-repo semantic code search MCP server in Rust — hybrid vector + BM25 retrieval, tree-sitter AST chunking, fully offline. For OpenCode, Claude Code, Cursor, and any MCP client.
Apache-2.0 ★ 104 -
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.
MIT ★ 82 -
A general-purpose MCP (Model Context Protocol) server for processing lecture materials from PDFs. Extracts text, chunks it for LLM processing, and converts to clean Markdown with LaTeX support using Google Gemini AI.
MIT -
🧠 Production-ready MCP server providing intelligent memory for Claude Code with async architecture, Neo4j knowledge graphs, smart chunking & enterprise security. One-command Docker deployment.
MIT ★ 8 -
semcode-mcpgithub.com/huawang1258/semantic-code-mcpupdated this year
Semantic code search MCP server: Tree-sitter AST chunking + voyage-code-3 embeddings + hybrid retrieval (sqlite-vec + FTS5 + RRF) + Voyage rerank-2.5 + call graph expansion. Thin npx wrapper that launches the Python package via uvx.
npm MIT -
RepoMindgithub.com/akshith120/RepoMindupdated this year
An intelligent, AI-driven codebase analytics engine powered by Retrieval-Augmented Generation (RAG). It performs precise repository analysis with hybrid search. language-aware AST chunking, exact line-level citations, and MCP (Model Context Protocol) tools for seamless integration with IDEs and AI agents.
★ 1 -
pythia-lcsupdated this year
Local code search and architectural memory MCP server for AI coding agents. Hybrid retrieval (vector + FTS + reranker) with Tree-sitter AST chunking. Runs entirely on your machine.
npm FSL-1.1-ALv2 -
Self-hosted semantic code search MCP server for Claude Code, Cursor and Codex: tree-sitter AST chunking, symbol graph, git history, local Qdrant + llama.cpp embeddings.
npm MIT -
High-performance, pure Rust multi-format eBook engine (EPUB2/3, MOBI, AZW3, KFX, FB2, LIT,MD,TXT,PDF, CBZ) with native Model Context Protocol (MCP) server, Okapi BM25 AI/RAG chunking, Readium CFI locators, zero-copy search, Python wheels & WASM.
pypi MIT ★ 15 -
Code-search platform for AI coding agents: vector search fused with BM25 keyword scoring and reranking, tree-sitter AST chunking, a web app, a REST API and a 12-tool MCP server.
MIT ★ 11 -
Filesystem-first hybrid vector memory engine & MCP server in Go. Couples human notes (Obsidian/Copyparty) with PostgreSQL + pgvector, hybrid RRF search, graveyard safety guardrails, and parent-child chunking for nomic-embed-text-v2-moe.
-
nethack-mcpgithub.com/NiJingzhe/nethack-mcpupdated this year
An MCP server that lets AI agents play NetHack. It spawns NetHack under a pseudo-terminal, parses the rendered screen into an LLM-friendly structured state, and exposes a small action DSL so the agent can emit action chunks instead of single keystrokes.
★ 2 -
Hierarchical knowledge base for AI. An MCP server that indexes your documents into a trigger-navigable node/chunk graph with hybrid retrieval — a permanent vault, no decay. Runs standalone or behind the Gray Matter gateway.
NOASSERTION -
antiquarIOgithub.com/JCarrascoF/antiquarIOupdated this year
A privacy first (local) document parsing tool and MCP server — convert PDFs and images to structured Markdown using multiple selectable OCR engines. Includes Streamlit GUI and hierarchical chunking for RAG workflows.
MIT -
codemindgithub.com/twly7ho2/codemindupdated this year
CodeMind is an AI agent memory system that maintains persistent, real-time context over complex codebases. By utilizing symbol graph storage, AST chunking, and intelligent file scanning, CodeMind enables LLMs to reason about relationships across large code structures without losing track of dependencies
★ 1 -
quriogithub.com/irahardianto/qurioupdated this year
Self-hosted RAG engine for AI coding assistants. Ingests technical docs & code repositories locally with structure-aware chunking. Serves grounded context via MCP to prevent hallucinations in software development workflows.
MIT ★ 17 -
MCP-Filesystem-Agentgithub.com/Mdskun/MCP-Filesystem-Agentupdated this year
Token-efficient MCP server giving Claude scoped read/write/search access to your local filesystem — chunked reads, dry-run edits, and multi-language code structure search, with segment-aware path validation.
MIT -
LangChain-based MCP server example that indexes local Markdown and text files, splits them into searchable chunks, and exposes document search and retrieval tools over Streamable HTTP. The repo includes open-source-only dependencies, architecture documentation, automated tests, and verified coverage.
MIT ★ 2 -
Turns a sprawling YouTube playlist into the mood playlists you actually reach for — chunk by workout, commute or late-night. Python CLI + MCP server; reads public lists with no API key, OAuth only when you write.
MIT -
Parses a web page into the exact format a decision model needs: dates as dates, numbers with units, chunks that fit the model's window. MCP server + TypeScript library, no model or API key required.
MIT ★ 5 -
Self-updating church sermon knowledge base — a daily job syncs sermons from a ministry API, transcribes them with OpenAI Whisper, semantically chunks and embeds them with Claude into SQLite (FTS5 + vectors), and answers members' questions via a chat UI and MCP
-
Web pages and PDFs to clean, LLM-ready Markdown as a remote MCP tool (Claude, Cursor, VS Code) and via the Apify API. Token counts, small crawls, sitemaps, RAG chunks, respects robots.txt. Python and Node examples.
MIT -
Local MCP server for semantic code search. AST-aware chunking with tree-sitter, offline ONNX embeddings, hybrid vector + BM25 (RRF) ranking, one SQLite file. No API keys or cloud. Semantic code search for Claude Code, Cursor, opencode and AI coding agents.
MIT