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.
-
Local institutional learning engine for AI agents — capture, curate, and publish reusable learnings via MCP
MIT ★ 7 -
kiro-learngithub.com/brendangeck/kiro-learnupdated this year
Continuous learning for Kiro agent sessions on AWS. Passive tool-use capture, LLM extraction, and synchronous context injection — inspired by claude-mem, aligned with Bedrock AgentCore Memory.
npm Apache-2.0 -
Self-learning issue memory for Codex using MCP. Automatically captures reusable bug fixes and reuses them across sessions with local-first, low-token SQLite storage.
MIT -
Robot learning stack for a real WidowX AI arm: demo capture, calibrated MuJoCo digital twin, Diffusion Policy with real-time chunking, π₀.₅/LeRobot in Docker, and LLM tool-calling control over MCP.
NOASSERTION -
@kamillion/librarian-mcpgithub.com/kogbuze/librarianupdated this year
Knowledge capture MCP server - remember what you learn with AI
npm MIT -
@telvok/librarian-mcpgithub.com/telvokdev/librarianupdated this year
Knowledge capture MCP server - remember what you learn with AI
npm MIT -
decision-os-mcpgithub.com/marianstefi20/decision-os-mcpupdated this year
MCP server for Decision OS — LLM-native decision tracking and learning system that captures novel pressure and compresses it into reusable foundations
-
Persistent memory for Claude Code and Pi with native Skills integration, automatic capture, failure learning, and project scoping
npm MIT -
Local-first engine that grounds an AI agent's answers in your own Markdown and captures what it learns back into the KB — Node · TypeScript · MCP.
MIT ★ 5 -
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 -
Persistent memory plugin for Kimi Code CLI — auto-capture, semantic vector search, user profile learning, Web UI. Port of opencode-mem. Kimi Code 持久记忆插件。
MIT -
MCP server over an Obsidian knowledge vault — BM25 retrieval plus one wiki-link hop, guarded writes, automatic learning capture, and link-safe move/rename/delete, each committed to the vault's git. README also in Português.
npm MIT -
subcoggithub.com/zircote/subcogupdated this year
Persistent memory system for AI coding assistants. Captures decisions, learnings, and context from coding sessions. Features hybrid search (semantic + BM25), MCP server integration, SQLite persistence with knowledge graph, and proactive memory surfacing. Written in Rust.
npm MIT ★ 30 -
youtube-obsidian-mcpgithub.com/mohsinkhadim59/youtube-obsidian-mcpupdated this year
Automatically generate professional Obsidian study notes from YouTube videos using Claude AI. Extract subtitles, capture screenshots at key timestamps, and create beautifully formatted markdown notes. Perfect for learning programming, design, academics, business - any topic on YouTube!
MIT ★ 3 -
Team knowledge evaporates daily — pairing sessions, debugging context, architectural rationale lost to Slack. Distillery captures it at the point of creation, connects it into a living graph, and surfaces it conversationally. It monitors feeds, tracks what matters to your projects, and alerts you before you know to ask. A team brain that learns.
NOASSERTION ★ 25 -
Schematic capture for neural network architectures. Draw the model, get the numbers, generate the PyTorch.
npm NOASSERTION -
autologygithub.com/Curt-Park/autologyupdated this year
A Claude Code plugin that turns AI-assisted work into a shared living ontology. Captures decisions, conventions, and context autonomously into typed, interlinked knowledge nodes (git-committed markdown). Navigate the ontology as a graph, trace conceptual paths between ideas, and catch doc-code drift before every commit.
MIT ★ 25