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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. 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.
-
ostk-recallgithub.com/os-tack/ostk-recallupdated this year
Local-first cross-corpus retrieval MCP server — model2vec embeddings + LanceDB (Tantivy BM25) + SQLite. One binary; hybrid (dense + BM25) search across markdown, code, and Claude Code sessions.
Apache-2.0 ★ 6 -
needlegithub.com/alexandremourin/needleupdated this year
Semantic code search MCP server: tree-sitter chunking + local Model2Vec embeddings + BM25/dense hybrid (RRF). Hands an AI only the relevant code (file:line), ~10-100x fewer tokens. Multi-language, no API key.
MIT -
Fast hybrid code search for agents. Pure Go, drop-in MCP-compatible with semble.
go MIT ★ 34 -
Fully offline semble: hybrid code search CLI and MCP server, with the model and grammars bundled
MIT -
Velesgithub.com/julymetodiev/Velesupdated this year
Fast hybrid (BM25 + semantic) local code search for AI agents - pure Rust, persistent index, MCP/gRPC servers, tree-sitter symbols
cargo ★ 9 -
triforgegithub.com/ilyasmukiev/triforgeupdated this year
One install, three MCPs: graph chat memory + semantic code search + backend. Benchmarked with claude-haiku-4-5: -19% tokens & 23× faster on memory-recall questions.
Apache-2.0 ★ 1 -
A unified web extraction and stateful automation engine for AI. Replaces heavy testing frameworks with token-optimized browser control, deep research, and HITL.
go MIT ★ 71 -
nesiftgithub.com/scottgl9/nesiftupdated this year
Fast, local semantic search over web content for AI agents. Hybrid BM25 + potion-retrieval-32M embeddings, cross-page dedup, token-budget mode, MCP server, SearXNG bridge. ~90% fewer tokens than raw web_fetch.
GPL-2.0 ★ 4