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.
-
Local-first MCP server for persistent semantic memory, backed by an HNSW vector index and an on-device ONNX embedder
MIT -
cocoindex-hnsw-lancedbgithub.com/systemgroupnet/cocoindex-hnsw-lancedbupdated this year
Cocoindex-based code indexing service with HNSW, automatic disk compaction, MCP Server, periodic git pull, metrics push to MySQL, and space-efficient branch searching
Apache-2.0 ★ 8 -
fusionpact-vectordbgithub.com/FusionpactTech/fusionpact-vectordbupdated this year
⚡ The Agent-Native Retrieval Engine — Hybrid Vector + Reasoning + Memory for AI Agents. HNSW indexing, tree-based reasoning retrieval, multi-agent orchestration, MCP server, and built-in RAG.
npm Apache-2.0 -
Deterministic evidence about embedding spaces and vector indexes for agents: hubness, anisotropy, collapse, distance concentration, ANN recall, HNSW/IVF sweeps. CLI + MCP server.
pypi MIT ★ 1 -
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 -
mcp-memorygithub.com/corporatepiyush/mcp-memoryupdated this year
MCP server giving LLM agents persistent memory: a SQLite knowledge graph with FTS5 search, tree-sitter code indexing (10 languages) with semantic code search, and optional vector + hybrid search (usearch HNSW or IVF-Flat) with batch upsert, more-like-this, recommendations, and MMR diversification
cargo Apache-2.0 -
trustswarmgithub.com/mrkingsleyobi/trustswarmupdated this year
Real-time blockchain fraud detection using autonomous multi-agent AI swarms. Detect fraud in <2s with 150x faster vector search (HNSW), 84.8% accuracy, and 73% cost reduction. Features ERC-1155 trust scores, MCP integration, and reflexion learning.
MIT ★ 1 -
Memory backbone for AI agents. Four-tier store — working, episodic, semantic, procedural — with decay, consolidation, and association graphs. Fused semantic + SIMD-accelerated hybrid recall, in-process MCP, REST/gRPC, and language SDKs.
npm Apache-2.0 ★ 28