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.
-
A Linux DJ studio and DAW that a human and an AI agent play together over MCP. Arrangement with mixer and automation, a modular synthesizer with synths, drums and effects, VST3/LV2 hosting, stem separation, live coding, warp. Public beta.
AGPL-3.0 ★ 1 -
Neo4j MCP server — free cloud Neo4j graph database with Cypher for Claude, ChatGPT and AI agents
MIT -
BloodHound-MCP-AI is integration that connects BloodHound with AI through Model Context Protocol, allowing security professionals to analyze Active Directory attack paths using natural language instead of complex Cypher queries.
★ 385 -
thought-mcpgithub.com/RNBBarrett/thought-mcpupdated this year
Local MCP memory server for LLMs. Bi-temporal graph + vector + Cypher queries + auto-write/auto-recall hooks for Claude Code. Works with Ollama, LM Studio, Anthropic, OpenAI.
MIT ★ 1 -
Read SEC and ESEF XBRL filings locally: parse once with Arelle into a portable model, export to TAVI, xBRL-JSON, JSON-LD or a LadybugDB property graph (one filing or many stacked), and query it with Cypher or from any MCP client.
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.
MIT ★ 931 -
Supply-chain incident response on a HydraDB graph: which of your services resolved a compromised version, which installed it while it was still live on npm, and the Cypher that proves each answer.
MIT ★ 2 -
本项目提供一个专业的 MCP 服务器,让 AI 助手(如 Claude、Cursor、Cline 等)能够直接访问和查询德国家族企业知识图谱数据库。通过 Neo4j 图数据库存储结构化知识,支持复杂的关系查询和语义搜索。
★ 1 -
A fast embedded graph database for AI applications and graph analytics
Apache-2.0 ★ 11 -
An MCP server that lets AI agents read and write an Ableton Live Set as a graph.
MIT ★ 12 -
Model Context Protocol server for FalkorDB graph databases - enables AI assistants to query and manage graph data using natural language
npm MIT -
MCP server for RushDB, the database for AI: schema-first tools for Claude, Cursor and other MCP clients
npm Apache-2.0 -
thought-mcpgithub.com/rnbbarrett/thought-mcpupdated this year
THOUGHT — Temporal Hierarchical Object Union & Graph Hybrid Toolkit. A local MCP memory server with bi-temporal graph + vector + temporal layers, a query router, and a consolidation engine.
pypi MIT -
Local code intelligence for developers and AI agents. Connect code, docs and infrastructure in a persistent graph, with CBM Lens, MCP tools, agent integrations and change-aware test selection.
npm MIT ★ 48,652 -
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.
pypi Apache-2.0 ★ 187 -
z-codebase-memory-mcpgithub.com/dajneem23/z-codebase-memory-mcpupdated this year
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
★ 8 -
AI Architect Codebase: cross-platform code intelligence MCP for Claude Code, Codex, Gemini, Cursor, VS Code, and Zed. Tree-sitter AST to LadybugDB graph, hybrid search, and impact analysis.
MIT ★ 7 -
Shared FalkorDB context graph for coding agents: a ~200-token map before the first tool call, memory across sessions, edit claims between agents. 144 Claude Code runs: −25% tokens, −29% tool calls. No LLM calls, no Docker.
MIT