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.
-
Vectorless, structure-first retrieval over large Markdown libraries for agents: section trees, mixed Chinese/English BM25 in SQLite, five read-only tools (AI SDK, MCP) and a built-in evidence loop
npm MIT -
Vectorless agent memory. HTML storage + grep retrieval. LongMemEval-S R@5 = 98.9%. No embedding, no vector DB.
MIT -
Second Brain for AI Agents — uniting Andrej Karpathy's LLM Wiki Pattern (Obsidian + raw/ + log.md + lint) with Nick Saraev's Vectorless Engram SQLite FTS5 BM25 + Recency Weighting MCP Server.
MIT -
Explainable, vectorless RAG for AI agents: BM25 + temporal knowledge graph over your files, served over MCP. R@5 0.977 on LongMemEval-S, ~2 ms queries, 0 LLM calls, zero dependencies.
MIT ★ 1 -
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.
Apache-2.0 -
fusionpactgithub.com/fusionpacttech/fusionpact-vectordbupdated this year
The Agent-Native Retrieval Engine — Hybrid Vector + Reasoning + Memory for AI Agents. HNSW indexing, tree-based reasoning retrieval, built-in RAG, MCP server, multi-agent orchestration, and agent memory architecture.
npm Apache-2.0