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.
-
unchgithub.com/uchebnick/unchupdated this year
Local-first semantic code search for repository annotations via GGUF embeddings and sqlite-vec.
Apache-2.0 ★ 15 -
sovereign-braingithub.com/sophiacave/sovereign-brainupdated this year
Local-first persistent memory for AI agents. SQLite + sqlite-vec. Semantic search, graph relationships, anti-hallucination. Zero cloud dependency.
MIT -
sovereign-braingithub.com/sophiacave/sovereign-brainupdated this year
Local-first persistent memory with semantic search. sqlite-vec powered. No cloud.
pypi MIT -
Search your Claude Code conversation history with an MCP server — full-text, semantic, and hybrid search over local transcripts, backed by SQLite + sqlite-vec.
-
Long-term memory for AI agents: one SQLite file, local embeddings, hybrid recall (sqlite-vec + FTS5), rules-based consolidation into facts and procedures. MCP server + CLI, no cloud.
MIT -
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 -
Long-term memory for AI agents as an MCP server: typed records searched by meaning and a directed knowledge graph between projects. SQLite with sqlite-vec or PostgreSQL, in-process ONNX embeddings, one local HTTP server for every session.
MIT -
AI-powered codebase intelligence platform — MCP Server, AST analysis, Knowledge Graph, and semantic memory with SQLite + sqlite-vec. Analyze any codebase in minutes.
MIT ★ 12 -
Persistent long-term memory for Claude Code agents — SQLite + FTS5 + sqlite-vec + RRF hybrid recall over MCP, with Chinese tokenization. Local-first, graceful degradation.
MIT ★ 8 -
Offline Polish↔English translation & terminology MCP server for LLM agents: Argos Translate MT, SQLite FTS5 dictionary lookup, bge-m3 + sqlite-vec translation memory. Air-gapped after install; every result carries source and license.
-
System 3 MCP server — persistent identity, memory, and self-model for AI agents. Single-file sqlite-vec + fastembed; zero external services.
npm AGPL-3.0 ★ 1 -
nxopen-mcpgithub.com/mingfeng6684/nxopen-mcpupdated this year
MCP server giving AI coding agents accurate Siemens NXOpen .NET API knowledge via hybrid retrieval (BGE-M3 + sqlite-vec), built from your own licensed NX installation
MIT ★ 21 -
万忆 · 永不遗忘的全量记忆系统 — MCP 标准 stdio + 事件溯源 + 过程记忆 + 语义向量检索 + sqlite-vec ANN + reranker 精排 + 记忆图谱 + 元认知知识空白 + 只读 Markdown 镜像 + 护城河全自动，23 个 MCP 工具。
MIT ★ 3 -
Local-first semantic memory for AI agents — time-travel, contradiction radar, automatic synthesis. MLX (Apple Silicon) or CPU sentence-transformers (Linux) embeddings + sqlite-vec, MCP server. No cloud, no API keys.
pypi MIT -
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 -
lumengithub.com/ory/lumenactive
Save 30% token costs when using Claude Code, Codex, OpenCode for free - with open source, local semantic search. Works for small and large codebases and monorepos! Enterprise-ready and fully compliant via Ollama and SQLite-vec.
NOASSERTION ★ 318 -
memogithub.com/jagoff/memoactive
Your coding agent starts every session with amnesia — memo fixes that, 100% on your machine. Persistent memory for Claude Code, Codex, Cursor & any MCP client: Markdown source of truth, hybrid search (MLX/CPU + sqlite-vec), time-machine, contradiction radar, nightly self-optimization. No cloud, no keys.
MIT ★ 27 -
Personal Telegram knowledge base — forward anything, search via DM. Hybrid SQLite + FTS5 + vector + voice, MCP server for Claude.
MIT ★ 13 -
Lightweight, zero-daemon local hybrid search engine powered by SQLite and fastembed
MIT -
Give AI agents (Claude Code, Cursor, MCP) eyes and ears over your video library with zero cloud dependencies.
MIT ★ 1 -
Searchable memory for your Claude Code sessions: local hybrid search with reranking, a CLI, and an MCP server for agents.
npm MIT -
Self-hosted mail search for AI agents: a synced local copy of your mailbox, searchable by keyword and by meaning over MCP. Read-only.
MIT -
smritigithub.com/moltizmo/smritiupdated this year
Local-first persistent memory for AI agents via MCP. Sanskrit for memory (स्मृति). Zero cloud. Zero cost.
MIT ★ 1 -
Local code search, import navigation, and bounded context for coding agents via CLI + Skill or MCP.
npm Apache-2.0 -
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 -
smritigithub.com/moltizmo/smritiupdated this year
Local-first persistent memory MCP server for AI agents — with consolidation loop and git sync
npm MIT -
querywise-mcpgithub.com/kosminus/querywise-mcpupdated this year
An MCP server (and a CLI) that lets an LLM query your databases in natural language through a business semantic layer — glossary, metric definitions, data dictionary, knowledge base, and example queries — grounded against your real schema.
MIT ★ 3 -
Fleet-grade local memory for AI agents over plain Markdown — hybrid recall, multi-tenant, one process, no cloud/Docker/LLM
MIT ★ 1 -
MCP server for Paperless-ngx: local semantic search with passages, safe filing and notes, and separate libraries per audience
ISC -
Free web search and long-term memory for AI assistants via MCP. No API keys; cache, memory and index stay local.
npm ISC