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.
-
Graph-based MCP server for systematic debugging using Problem-Solution Trees and Hypothesis-Experiment-Learning cycles
npm MIT -
Local-first personal knowledge management (PKM) MCP server and learning memory for every AI tutor—goal trees, a reusable knowledge graph, and evidence-gated mastery.
mcpb Apache-2.0 -
Learnlog MCP: ask your AI assistant what learning records actually show about help. Read-only tools for Learnlog records, QLM credential verification, and QLM's public misconception and learning-graph datasets.
npm Apache-2.0 -
qortexgithub.com/peleke/qortexupdated this year
Knowledge graph that learns from every interaction. MCP server, graph retrieval, adaptive learning.
pypi MIT -
Local-first learning tool: a concept-graph dashboard over plain files, with an MCP server so AI can weave lessons, tests and roadmaps.
npm MIT -
Persistent memory MCP server for AI agents — Rust, 19 tools, knowledge graph, Hebbian learning, episodic memory, contradiction detection, prospective triggers, Bayesian calibration, zero-config Docker setup.
npm Apache-2.0 ★ 30 -
@swarmrecall/mcpgithub.com/swarmclawai/swarmrecallupdated this year
Model Context Protocol server for SwarmRecall — exposes memory, knowledge graph, learnings, skills, pools, and dream tools to any MCP-compatible agent over stdio
npm MIT -
Issue router that learns which team owns what from the issues that actually get fixed. Weighted path search on a HydraDB graph, a React dashboard, and an MCP server for AI agents.
GPL-3.0 ★ 1 -
knowledge-graph-mcpgithub.com/zcsabbagh/knowledge-graph-mcpupdated this year
MCP server for tracking student learning via a knowledge graph with spaced repetition
pypi MIT ★ 2 -
graphonomousgithub.com/c-u-l8er/graphonomousupdated this year
Continual learning MCP server for AI agents — topology-aware knowledge graph with kappa-routing, exposed as 5 loop-phase machines (retrieve/route/act/learn/consolidate), causal metadata, and neural embeddings. One of four MCP servers in the [&] three-prot
npm Apache-2.0 -
Learn while your agent works. A Claude Code plugin that quizzes you on the concepts behind the code it just wrote — local knowledge graph, spaced repetition, optional commit gate.
npm MIT ★ 29 -
Agent-first adaptive learning platform. Create courses as YAML knowledge graphs via CLI or MCP server. AI agents scaffold, fill, review, and publish — no UI required. Adaptive diagnostics, spaced repetition, white-label sites.
npm NOASSERTION ★ 3 -
Permanent code intelligence layer. Learns what matters, expires what changed, proves what existed. Content-addressed graph with Merkle proofs, 25 extractors, 23 MCP tools. Gets smarter with use.
pypi Apache-2.0 ★ 24 -
ainl-cortexgithub.com/sbhooley/ainl-cortexupdated this year
Graph-native memory and self-learning for Claude Code. Every session remembered, every pattern learned, every agent connected — powered by AI Native Lang.
pypi NOASSERTION ★ 4 -
Just applying my learnings about Text2SQL, VectorDB, Knowledge Graph, MCP!
-
hyphaegithub.com/dgtise25/hyphaeupdated this year
Code intelligence MCP server — turns your repos into a self-learning knowledge graph for Claude Code
npm MIT ★ 2 -
@alexdx/chronicle-mcpgithub.com/alexdx2/chronicleupdated this year
Chronicle MCP — self-learning knowledge graph for code analysis. MCP server for Claude Code.
npm MIT -
Self-learning AST context engine & knowledge graph optimized for Laravel codebases and AI coding agents
npm MIT -
learningOS-MCPgithub.com/mateuszpoland/learningOS-MCPupdated this year
MCP server for managing learning knowledge graph
-
MCP server providing long-term memory for AI agents — knowledge graph with Qwen3 embeddings, continuous learning, and knowledge evolution
MIT ★ 6 -
Your team's engineering memory for coding agents: one graph of your repositories and what the team learned, in your own storage, served over MCP.
cargo MIT ★ 1 -
The experience graph for AI agents. Self-hosted memory, human-reviewed decisions, and outcome-backed datasets for model evaluation and learning.
npm Apache-2.0 ★ 23 -
Graph context layer for AI coding agents on self-hosted HydraDB v0.4.0: 64-tool continual learning, 2-hop AST blast radius, and temporal ADR supersession (MCP, CLI, 3-tab UI).
MIT -
Self-improving code context for coding agents. MCP server that walks a code graph in HydraDB and learns from every merged PR. Launches the klew Python package via uvx.
npm MIT -
Local-first compounding intelligence for AI agents. Experience Graph, Memory Bank, Growth Merge, learned skills. MCP-native for any model. MIT.
MIT -
Turn any repo into an interactive code graph, a learning roadmap, an AI pipeline security audit and an MCP server for AI assistants. One CLI, fully offline.
MIT ★ 1 -
Local-first MCP server for persistent engineering memory, 26 specialist agents and repository dependency graphs. Human-governed learning for Claude Code, Codex and VS Code.
pypi Apache-2.0 -
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 -
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 -
A memory of the codebase your AI agent can't get from grep: a persistent call graph, semantic search, and per-symbol review learnings over any repo. Self-hosted MCP server — Go, tree-sitter, Apache AGE.
go Apache-2.0 ★ 6 -
An agent that learns how you think and choose, and lends that to the AI tools you already use. Time-aware knowledge graph, a body map of what it knows, and hooks, MCP and HTTP for other AI.
-
Cortivexgithub.com/AhmedRaoofuddin/Cortivexupdated this year
AI agent pipeline orchestration for Claude Code. Deploy specialized agents in coordinated pipelines with self-learning capabilities, mesh coordination, Raft consensus, CRDT knowledge graphs, and pipeline debugging. 15 production-grade skills with reasoning protocols, 20+ agent types, 15 ready-to-run templates. Zero infrastructure.
npm NOASSERTION ★ 12 -
A specialized MCP server that tracks your Python development sessions, errors, fixes, and coding patterns using a persistent knowledge graph. This helps you build a searchable database of your development learnings, solutions, and insights.
pypi MIT -
Living memory system for AI assistants — SQLite + MCP with decay, learning, and knowledge graph
npm MIT ★ 1 -
An MCP server that turns 1001 Solana glossary entries into intelligent LLM tools - lookup, search, graph-based concept exploration, learning paths, side-by-side comparisons, and random discovery. With full i18n support (🇺🇸 🇧🇷 🇪🇸). Built on top of @stbr/solana-glossary SDK.
MIT -
Auditable deterministic reasoning MCP server (non-LLM). World-graph → A* auditable reasoning → execution → learning loop. Fail-closed: an unchecked claim is never returned as passed. Free for non-commercial agent use.
npm NOASSERTION -
synapseflowgithub.com/mrkingsleyobi/synapseflowupdated this year
🧠 Self-learning AI research assistant with 66-agent orchestration, MCP server, and real-time citation graph visualization. Process 1000+ papers/minute with 150x faster vector search.
MIT ★ 2 -
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 -
**Persistent memory for AI agents that you can actually read.** Kybase stores what your agent learns as plain Markdown notes with `[[wikilinks]]`, searched by keyword and by meaning. It runs locally: notes live in an embedded Postgres on your machine (`~/.kybase`), with no Docker, no server and no account. **What your agent gets (18 tools)** - **Search** — `search_notes`: hybrid keyword + semantic search that returns the section each excerpt came from - **Read** — `get_note` (whole, windowed or one section), `list_notes`, `list_tags`, `list_folders`, `indexing_status` - **Write safely** — `create_note`, `append_to_note`, `replace_in_note`, `update_note` with conflict protection, `delete_note` / `restore_note` (trash) - **Link** — `get_backlinks`, `get_neighbors`, `get_graph` over the wikilink graph - **Organize** — `create_folder`, `update_folder`, `delete_folder` **Setup** Keyword search works right away. For search by meaning, pick an embedding provider in the settings: local **Ollama** (`ollama pull embeddinggemma`) keeps everything on your machine; **Google** or **OpenAI** need an API key and send note text to that provider. **Your data stays yours** `kybase-mcp export vault.zip` writes every note out as plain Markdown, folders as directories, readable in any editor, Obsidian included. **Want a UI?** The full Kybase app adds a web editor, a knowledge-graph view, share links, and one memory shared by Claude Code, claude.ai and Cursor: [github.com/Kyrzin/kybase](https://github.com/Kyrzin/kybase) Open source, AGPL-3.0.
smithery -
Contextualno update data
## Contextual — Persistent Memory for AI Coding Agents AI coding agents forget everything the moment your session ends. **Contextual** fixes that by giving any MCP-capable AI client — for developers who use multiple AI coding tools at once — a real, persistent memory of your codebase: not just what the code says, but what changed and why. It's a **local-first MCP server**: your code, your index, and every query stay on your machine. The only network call is a lightweight, infrequent license check — no code, ever, leaves your device. Under the hood, Contextual builds a real understanding of your repository, not a text-similarity guess: - **Structural search** — tree-sitter AST parsing + call-graph resolution, so agents reason about how your code actually connects. - **Bitemporal history** — tracks not just when your code changed, but when the AI learned about it. Ask "did this bug fix happen before or after the agent's understanding of this function?" and get a real answer. - **Git-aware retrieval** — temporal, history-grounded context instead of a stale snapshot. - **Fast, self-contained** — index a 50k-line repository in about 5 minutes, then query it in ~94ms median, from a single ~0.8GB install. This extension connects Claude Desktop (or any MCP-capable client) to a Contextual installation already set up and activated on your machine — it does not provision Contextual from scratch.
smithery -
Graph-based retrieval for Obsidian vaults with Hebbian synaptic plasticity
MIT ★ 2 -
Solvro internal MCP server
★ 6 -
Advanced Graph RAG MCP Server with sophisticated graph structures, operators, and agentic capabilities for AI agents
npm MIT -
Advanced Graph RAG MCP Server with file location identification, graph processing, and result summarization capabilities
npm MIT -
AI Intelligence Platform -- knowledge graph + semantic search + reasoning + multi-agent debate in a single binary
NOASSERTION ★ 20 -
MCP server for Lynkt knowledge graph integration with Claude Desktop
npm MIT -
Your AI agent's codebase map. Local-first, hybrid-search code graph for 51+ languages & formats. MCP server. 100% private.
pypi MIT ★ 2 -
FedCtx — Federated Semantic Infrastructure: HNSW + Graph + Audit + Memory + gRPC + REST + MCP
NOASSERTION -
Learner-aware Python knowledge graph with GraphRAG retrieval, mastery-based recommendations, MCP tools, and an interactive demo.
-
Give your AI coding agent access to curated ML/AI knowledge.
MIT ★ 14 -
long-term-memorygithub.com/ihwooMil/long-term-memoryupdated this year
Intelligent memory MCP server for AI assistants — auto-save, semantic search, RL-powered retrieval, and knowledge graphs
pypi MIT -
Agent-native ML experiment tracking: write contract, code snapshots, knowledge graph, MCP server, live UI
Apache-2.0 -
Turn local and arXiv LaTeX papers into queryable theorem-proof dependency graphs for AI agents via MCP.
MIT -
DreamGraph is a graph-governed conceptual development environment (CDE) that turns plans, architecture decisions, and project knowledge into auditable execution through a persistent cognitive graph.
npm NOASSERTION ★ 128 -
mnemogithub.com/ArtLjn/mnemoupdated this year
Structured fact memory MCP server — SQLite + FTS5, trust scoring, entity graph, auto-observe, bilingual retrieval for AI coding assistants
MIT ★ 1 -
a knowledge-graph and RAG system that extracts requirements into neo4j, queryable through an ollama and MCP chat client with RL tuned retrieval strategies.
-
Provide AI agents with long-term memory using a neuroscience-based knowledge graph and Model Context Protocol for improved coding assistance.
NOASSERTION ★ 1 -
SynapCores Community Edition: free self-hosted AI database (SQL, vector search, graph, in-database ML, agent memory, MCP). Install: curl -fsSL https://get.synapcores.com | sh
★ 1 -
hf-cligithub.com/tamnd/hf-cliupdated this year
Read huggingface.co as data: every model, dataset, space, user, org, collection and paper as a typed record with an hf:// URI and a knowledge graph of the edges between them
Apache-2.0 ★ 1 -
Neuroscience-inspired memory for AI agents — sleep cycles that rewrite and strengthen knowledge over time. TypeScript, PostgreSQL, MCP.
npm MIT ★ 15