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.
-
markdown-fastrag-mcpgithub.com/lidge-jun/markdown-fastrag-mcpupdated this year
Fast markdown RAG with multi-provider embeddings (Vertex AI, Gemini, OpenAI, Voyage), incremental indexing with mtime/size fast-path, stale vector pruning, Milvus vector store.
Apache-2.0 ★ 5 -
lip-coregithub.com/simplyliz/lipupdated this year
LIP — persistent, incremental code intelligence graph. WAL-backed daemon, blast-radius indexing, MCP/LSP protocol, semantic embeddings, and registry slices.
cargo MIT -
symtextgithub.com/ds7n/symtextupdated this year
Lightweight code graph indexer with incremental file watching and MCP server
pypi MIT -
codebase-mcpupdated this year
Persistent, portable codebase intelligence MCP server with incremental indexing and decision memory
pypi MIT -
coderag-gogithub.com/matperez/coderag-goupdated this year
Index and search code with BM25 and optional embeddings. Go-based MCP server (codebase_search, index status), incremental indexing, AST chunking.
MIT -
ccegithub.com/aidesuwa/cceupdated this year
MCP server providing semantic code search with automatic incremental indexing, powered by Augment Code
MIT -
Lightweight code indexing and exploration powered by Lua, with multi-language symbol extraction, call graphs, and incremental updates.
npm BSD-2-Clause -
Git-aware code knowledge graph — incremental AST indexing on every commit, MCP server for AI assistants
pypi MIT -
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 -
corpus-search-mcpgithub.com/TheBitcoinBreakdown-95/corpus-search-mcpupdated this year
MCP server for search over any folder of markdown, with incremental indexing and a runnable retrieval eval
MIT -
@jokeran/java-repo-skimmeractive
Java repository intelligence MCP with unified query, call graph, data flow, Spring analysis, and incremental indexing.
npm MIT -
Local documentation retrieval for agents: MCP over stdio and HTTP, incremental SQLite indexing, source citations, and a bounded agent loop.
MIT ★ 2 -
轻量级代码智能 MCP:AST + 增量索引 + 调用图,无 embedding。Lightweight code intelligence MCP: AST, incremental index & call graph.
MIT -
Week-stamped, incremental index of Claude Code session transcripts: embedded PocketBase + LanceDB replica, Rust watcher, macOS tray, HAOS add-on, MCP with OAuth
MIT -
scout-code-navigatorupdated this year
MCP server for fast, incremental code navigation - no indexing, no embeddings, no waiting
pypi MIT -
Evidence-grounded repository intelligence with incremental code indexing, AST extraction, code search, engineering memory, FastAPI, React and MCP tools.
NOASSERTION -
RAG-over-a-corpus MCP server. search_knowledge returns cited passages (source + heading + chunk index). Fully local, $0 embeddings, ChromaDB, incremental ingest.
pypi MIT ★ 1 -
pythiagithub.com/michaeljboscia/pythiaupdated this year
Local-first code & knowledge retrieval framework for AI agents: incremental indexing, semantic + lexical search, MCP server, pluggable embedding backends.
NOASSERTION -
Retrieval over a repo's current documentation, served to coding agents over MCP: declared corpus scope, incremental SQLite index, vector + FTS5 fusion.
MIT -
Semantic search over any markdown corpus, exposed as an MCP server. Local ChromaDB, markdown-aware chunking, incremental indexing. No API keys.
MIT -
emCPgithub.com/eeveere/emCPactive
Local-first semantic code retrieval for AI agents and developer tools, with incremental indexing, hybrid search, SQLite persistence, and MCP.
MIT ★ 1 -
semantic-code-searchgithub.com/n1ra7/semantic-code-searchupdated this year
Self-hosted, zero-cost semantic code search + RAG with an MCP server — FastEmbed embeddings, Qdrant vector DB, incremental indexing, and eval harness. Python.
MIT -
Local-first code context engine in Rust + DuckDB: incremental semantic indexing, hybrid search, MCP server, HTTP API and TUI. Rust rewrite of devai-context-engine.
MIT -
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 -
Self-hosted document search for MCP-compatible AI clients. Docker includes a web dashboard, Qdrant, incremental indexing, CPU/GPU embeddings, and backup/restore.
-
Code intelligence graph for AI coding agents. Combines graph traversal, semantic search, and BM25 keyword search in a single Memgraph-powered system. Indexes code structure, documentation, and dependencies with AST-level incremental updates. Monorepo-native. Self-hosted. MCP server included.
pypi Apache-2.0 ★ 7 -
Cross-agent Raw-RAG incremental memory indexer and MLX two-stage retrieval MCP server for Claude Code, Codex, OpenCode, Oh My Pi, and Antigravity
pypi MIT -
codebase-RAGgithub.com/bluewings1211/codebase-RAGupdated this year
A Retrieval-Augmented Generation (RAG) Model-Controller-Provider (MCP) server designed to assist AI agents and developers in understanding and navigating codebases.. It supports incremental indexing and multi-language parsing, enabling LLMs to understand and interact with code.
MIT ★ 15 -
Local-first personal knowledge base MCP server for Claude Code - your Markdown notes as the single source of truth. SQLite FTS5 search, frontmatter classification, incremental indexing, optional Ollama compiler. No embeddings.
★ 4 -
codegraph is a local-first code context engine and MCP server for repositories. It incrementally indexes source code into a lightweight SQLite graph, then exposes high-signal tools for symbol lookup, call graph traversal, impact analysis, related test discovery, and semantic search. Built in Go with a single-binary workflow, it is designed to work
go NOASSERTION ★ 4 -
Native Code Knowledge Graph plugin for Google Antigravity (AGY) powered by Tree-sitter AST, SQLite & code-review-graph. Features 22+ MCP tools, 9 workflow skills & deterministic zero-lag incremental indexing.
MIT -
Read-only MCP server for Calibre: metadata, BM25 full-text search over EPUB/PDF/MOBI/LIT, chapter/page reading, highlights. Direct SQLite (works with Calibre open), incremental FTS5 index, stdio + Streamable HTTP with bearer auth. Windows-first, cross-platform.
Apache-2.0 ★ 6 -
Local code search engine for AI agents: incremental indexer, hybrid retrieval (BM25 + dense embeddings in Qdrant, RSF, per-language reranker) and an MCP server. Tree-sitter chunking, git branch/tag overlays. Java, Kotlin, Groovy, C#, Go, PHP, Python, JS/TS, C/C++, Delphi/Pascal, SQL and more.
Apache-2.0 ★ 2 -
Shared memory for AI coding tools: hybrid search, cited Q&A, harness memory discovery and a built-in Web console. Local index, MCP + HTTP.
pypi MIT ★ 101 -
pmos-braingithub.com/feamando/brainupdated this year
Semantic Knowledge Graph with Graph Analytics, Event Sourcing, Enrichment Pipeline, Vector Search, MCP Server & Quality Scoring
pypi MIT -
Find source context and trace calls across languages in Claude Code, Codex and other MCP agents.
pypi Apache-2.0 ★ 95 -
A five-model knowledge graph over a directory you choose — built to prove itself wrong. SQLite + FTS5, stdlib-only, 100% local.
MIT -
codescope-aigithub.com/harsh-185/codescopeupdated this year
Turn any GitHub repo into a navigable, shareable website with AI-driven intent-diff for every commit. CLI + MCP server. Bring-your-own Claude/OpenAI keys.
npm MIT -
Fast, fully-local code search & navigation for large codebases — cuts the tokens an AI coding agent spends finding code. Lexical + symbolic + semantic, memory-mapped, no GPU, no cloud.
MIT -
Local RAG over a directory. Incremental. Served as MCP tool + CLI.
MIT -
Hybrid (vector + BM25) search over many markdown repos in one SQLite file, served over MCP for coding agents: per-hit AGENTS.md chains, link graph, archived-doc detection, incremental delta distribution.
MIT -
memorag-mcpupdated this year
Intelligent context management layer for LLMs — incremental memory, token-efficient retrieval, MCP server included
npm MIT