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.
-
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 -
Local-first MCP server for persistent semantic memory, backed by an HNSW vector index and an on-device ONNX embedder
MIT -
FedCtx — Federated Semantic Infrastructure: HNSW + Graph + Audit + Memory + gRPC + REST + MCP
NOASSERTION -
Native Rust AI orchestration CLI — zero Node.js dependency. 347 MCP tools. SONA neural net, Thompson bandit router, RuVector HNSW, real ONNX embeddings.
-
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 -
Zero-allocation Zig substrate: ITCH LOB, H3, HNSW, GGUF, Quant, Chess — 202 C ABI symbols, Python wheels, MCP server, and 33 KB WASM
MIT -
throne-showcasegithub.com/loki128/throne-showcaseupdated this year
Self-evolving multi-agent AI orchestration system. Genetic prompt evolution, swarm immune system, trust contagion, HNSW vector search, 50+ MCP tools. 14K+ lines. Architecture showcase — source is private.
★ 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 -
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 -
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 -
Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.
go MIT ★ 931 -
Local vector DB over MCP (stdio): flat/IVF/HNSW scans with a committed recall benchmark
MIT -
家用储能选型与报价:公开套餐溯源、LangGraph 研究与恢复、pgvector/HNSW 权限检索、JWT/MCP、SSE 与人工审核。
MIT -
Moteur de connaissance local-first en Rust : RAG hybride (HNSW + BM25), MCP, garde-fous Laya.
MIT -
memrustgithub.com/aianytime/memrustupdated this year
Agent-native memory engine: hybrid retrieval (HNSW + BM25 + entity graph + recency) behind remember/recall/forget, with HTTP and MCP interfaces
cargo Apache-2.0 -
rbraingithub.com/hongyuatcufe/rbrainupdated this year
Rust port of gbrain — single-binary personal AI knowledge base: SQLite + tantivy BM25 + usearch HNSW + CJK morphological tokenization + MCP server
★ 1 -
Legal RAG platform with LangGraph, MCP tools, and pgvector. Hybrid BM25+dense retrieval with RRF and HNSW. 119/119 tests passing.
MIT -
sqlrite-notesgithub.com/joaoh82/rust_sqliteupdated this year
Example: a Node.js CLI that ingests a folder of markdown notes into SQLRite (hybrid HNSW + BM25 retrieval), then exposes the database to Claude Desktop / any MCP client via sqlrite-mcp.
npm MIT -
RAG proof of concept: hybrid retrieval (pgvector HNSW + lexical RRF), cross-encoder reranking, dual embeddings (OpenAI + local GPU/CPU), and an MCP server — Python, PostgreSQL, Docker (NVIDIA/ROCm)
-
High-performance Technical Knowledge Base & MCP Server powered by PostgreSQL 17, pgvector (HNSW), Lexical Search (GIN), Reciprocal Rank Fusion (RRF), and Automated Technical Entity Graph Extraction.
MIT ★ 2 -
neurovaultgithub.com/hein4793/neurovaultupdated this year
NeuroVault - A self-evolving 3D knowledge brain that runs entirely on your machine. SQLite + FTS5, 31 autonomous circuits, HNSW vector search, Obsidian vault, MCP integration.
MIT ★ 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 -
Own your memory: Persistent, private memory for Claude via MCP - semantic recall over ObjectBox's embedded HNSW vector search, with local Ollama embeddings. Local-first, offline-capable, nothing leaves your machine. Keep your Memory when you change your AI.
Apache-2.0 -
MCP server giving AI agents (Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw) persistent long-term memory backed by your local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantizati
npm MIT -
Cortex - AI Agent 的第二大脑。单二进制本地知识库,MCP 原生支持,混合搜索 + Agent 记忆系统。
Apache-2.0 ★ 3 -
mnemogithub.com/omermaksutii/mnemoupdated this year
Persistent memory for Claude Code. Your AI never starts from scratch again.
npm MIT ★ 41 -
Vector memory that gets smarter every time your agent uses it.
npm MIT ★ 99 -
Multi-platform desktop viewer for MongrelDB: direct + server connections, schema map, SQL, dense ANN, MCP, and chat.
Apache-2.0 ★ 3 -
Local agent memory, coding loop, Cursor from Telegram, scheduled playbooks, and MCP tools.
npm MIT -
Semantic MCP tool-discovery gateway — find tools by intent, not memory.
npm MIT ★ 1 -
Memory system for AI agents with hybrid retrieval, MCP tooling, and LongMemEval-leading performance.
NOASSERTION ★ 3 -
The database built for AI agents - hybrid vector + BM25 + structured, durable, with RESP / MCP / gRPC servers. Apache 2.0.
pypi Apache-2.0 ★ 1 -
vector-memory-pggithub.com/cabupy/vector_memory_pgupdated this year
Institutional technical memory for AI coding agents using PostgreSQL, pgvector, hybrid search, MCP, Reflect, CLI, and local UI.
npm MIT -
Personal RAG engine — simple, fast, Rust. One binary (15 MB), one DB, native collections. MCP-native.
cargo ★ 6 -
Docker container for centralized Ruflo MCP server with PostgreSQL (RuVector). Architecture: Ruflo (stdio) → Express proxy (Streamable HTTP /mcp).
★ 4 -
Rust-native hybrid retrieval over LLM thinking traces - dense ANN + BM25 + rerank, all local ONNX. Daemon, HTTP + MCP, zero API keys.
Apache-2.0 ★ 1 -
Local-first memory for AI agents as an MCP server: semantic + keyword recall, typed memories, graph relations, audit log. npm: agent-memory-engine
MIT -
A Rust MCP server that turns a Postgres database into memory — 768d vectors, a typed knowledge graph for CHA0S AOE.
NOASSERTION -
rag-db-advisorgithub.com/kenimo49/rag-db-advisorupdated this year
An evidence-based advisor for RAG stack decisions — every claim backed by rag-retriever-bench measurements. MCP + CLI.
MIT -
amanmcpgithub.com/Aman-CERP/amanmcpupdated this year
AmanMCP is a local-first RAG MCP server for developers - providing hybrid search (BM25 + semantic) over codebases for AI assistants like Claude Code and Cursor.
go Apache-2.0 ★ 4 -
distillery-mcpupdated this year
Persistent shared memory for Claude Code — MCP server with DuckDB vector search, semantic dedup, and ambient intelligence for team knowledge
pypi Apache-2.0 -
Open-source Rust multimodal vector database & RAG platform: one unified space for text, image, audio, video & docs - hybrid search, reranking, built-in MCP server.
AGPL-3.0 -
An AI agent's own long-term memory, on your machine — a local MCP memory graph in Rust. No cloud; no LLM in storing or search.
npm NOASSERTION ★ 2 -
nexo-braingithub.com/wazionapps/nexoupdated this year
NEXO runtime core for NEXO Desktop. Provides local memory, Deep Sleep, Evolution support-ticket mode, skills, watchdog, and MCP tooling for the Desktop product.
npm AGPL-3.0 -
@freshair129/gksgithub.com/freshair129/gksv3updated this year
Genesis Knowledge System — a memory fabric for agentic AI built on the EVA Tri-Brain architecture. Four memory layers, bi-temporal versioning, multi-tenancy, OpenTelemetry, MCP server, and a CLI.
npm MIT -
MoFlo — an opinionated, local-first AI agent orchestration toolkit for Claude Code: semantic memory, learned routing, gates, and spells. No API keys, no cloud, works out of the box.
npm MIT ★ 19 -
Rust graph-vector database: OpenCypher (99.9% of evaluated TCK scenarios pass), vector search, graph algorithms, RESP + HTTP. LDBC SNB Interactive and BI complete; 1B edges on one machine.
cargo Apache-2.0 ★ 187 -
Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, and fades stale memories via temporal decay, written in Rust (Apache-2.0) as a library, MCP server, or HTTP cluster.
cargo Apache-2.0 ★ 180 -
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 -
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
npm MIT ★ 81,864