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.
-
The experience graph for AI agents. Self-hosted memory, human-reviewed decisions, and outcome-backed datasets for model evaluation and learning.
Apache-2.0 ★ 23 -
Local personal knowledge graph: plain-English facts → typed graph → context snapshot for any AI chat. Ollama, SQLite, MCP server. Paused; experiment write-up inside.
MIT -
Auditable research provenance as local-first MCP tools. The claim checker, paper feed, knowledge graph and symbolic math assume nothing about your field — any results JSON or CSV works, from any instrument. The experiment ledger adds W&B/MLflow/Sacred/DVC/Hydra for computational work. Nothing leaves the machine.
MIT ★ 1 -
knotgithub.com/dreygur/knotactive
Archived experiment: local code graph search and team learnings for AI coding agents (Claude Code, Codex, Cursor) as a Rust MCP server and CLI. Tree-sitter, BM25F and call graph ranking, benchmarked on Agent Retrieval Bench against Trail, CodeGraph, Serena and more. Abandoned: agents never used it.
MIT -
🗂️ Boost your Obsidian experience with a powerful Model Context Protocol server for vault access, knowledge graph analysis, and seamless integrations.
-
Scythe (ctx) is a live, auto-updating codebase context engine. It maintains a local SQLite relational graph of your repository, synced dynamically on edit by AI models, guaranteeing structured, zero-drift context under 10k tokens — even for million-line codebases.
Apache-2.0 -
Persistent reasoning memory for AI coding agents over MCP: decisions, evidence, corrections and experience history.
NOASSERTION -
Self-learning memory for AI agents — experience captured automatically, distilled into lessons overnight, shared across your whole fleet. Works with Hermes, OpenClaw, Claude Code, and Pi.
npm NOASSERTION ★ 3 -
Deterministic cognitive state substrate & world model runtime for autonomous agents. Features transactional belief updates, hybrid RK4 rollouts, and 3-tier experience consolidation via MCP & REST.
Apache-2.0 ★ 6