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.
-
@work-graph/mcpgithub.com/bvc-lang/work-graphupdated this year
MCP server for Work Graph — work items in intent/**/*.work.bvc
npm Apache-2.0 -
mcp-social-work-graphupdated this year
MCP server for knowledge graph operations with Neo4j
npm MIT -
task-graph-mcpgithub.com/Oortonaut/task-graph-mcpupdated this year
**Multi-agent AI coordination that actually works.** When you have multiple AI agents working on the same codebase, things go wrong fast. Agents overwrite each other's changes. They duplicate work. They break dependencies. Task Graph solves this with coordination primitives for tracking worker tasks and coordinating file changes.
cargo Apache-2.0 ★ 2 -
skill-graphgithub.com/feelfetch/skill-graphupdated this year
Graph-aware second brain MCP server for AI agents. Works with any markdown folder, with Obsidian as optional enhancement.
npm MIT -
Save 6-8× tokens on AI code reviews. Builds a structural call graph via Tree-sitter + MCP. Works with Claude, Kimi, Gemini, ChatGPT, Cursor, Windsurf — any AI assistant.
MIT ★ 2 -
Local-first drill-down work map and queryable knowledge graph with read-only MCP and optional Obsidian integration.
Apache-2.0 -
MCP server that turns an Obsidian vault into working memory for an LLM agent. Deterministic write guardrails in code, hybrid search (BM25 + vector + temporal + graph), automated retention pruning. Built for Claude Code, works with any MCP client.
MIT -
sparql-mcpgithub.com/rareba/sparql-mcpupdated this year
MCP server for SPARQL endpoints. LINDAS-aware, works with any SPARQL 1.1 endpoint / graph database.
Apache-2.0 ★ 1 -
lxDIG-MCPgithub.com/lexCoder2/lxDIG-MCPupdated this year
Dynamic Intelligence Graph (DIG) MCP server for AI coding agents. Persistent code knowledge graph, a code RAG improvement, with hybrid Graph + Vector + BM25 retrieval, agent memory, multi-agent coordination, and impact-scoped test selection. Works with Claude Code, VS Code Copilot, and Cursor.
★ 4 -
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 -
An MCP server that integrates with your OneDrive and Excel Workbooks, to enable creating and modifying work sheets using the Microsoft Graph API.
pypi -
YATS — Knowledge graph for AI coding agents. Cut code-reading tokens by 37–73%. Works with Codex, Claude, Copilot, Cursor & Gemini.
npm NOASSERTION -
miegithub.com/kraklabs/mieupdated this year
Persistent memory graph for AI agents. Facts, decisions, entities, and relationships that survive across sessions, tools, and providers. MCP server — works with Claude, Cursor, ChatGPT, and any MCP client.
go AGPL-3.0 ★ 44 -
Proactive work intelligence for engineering teams. Connects Linear, GitHub, Slack, Jira, Notion and Google Docs into one context graph, scores what deserves attention, and answers in Slack. Self-hosted, AGPL-3.0.
AGPL-3.0 ★ 2 -
agileplus-cligithub.com/phenotype/agileplusupdated this year
Typed intent graphs for engineering work — convert prompts into validated DAGs of intents, features, tasks, tests, and edges, then store, query, and serve them from Rust, HTTP, or MCP.
cargo MIT -
memoryvault-kitgithub.com/ayushmall/memoryvault-kitupdated this year
A personal memory layer for your AI tools. Intelligent authoring (gap detection, self-enriching graph, session-synthesis loop) + measurably good retrieval (94.9% blind Cov@10, sub-ms latency). Domain-agnostic framework — works for any context you want to track. MCP-native, Claude-Code-first, works with Cursor/Continue/Cline/OpenAI/Gemini.
MIT ★ 2 -
Graph-based memory system for AI agents. Store people, places, organizations as nodes. Build semantic relationships (KNOWS, WORKS_AT, CREATED). Word-tokenized search finds partial matches. Filter by date, traverse relationships, maintain temporal context.
npm MIT -
tremulagithub.com/Firsak/tremulaupdated this year
Self-maintaining code memory for AI coding agents: an Obsidian-compatible knowledge graph of your codebase, served over MCP and auto-curated from your work sessions.
MIT ★ 1 -
tremula-mcpupdated this year
Self-maintaining code memory for AI coding agents: an Obsidian-compatible knowledge graph of your codebase, served over MCP and auto-curated from your work sessions.
pypi MIT -
codexraygithub.com/NeuralRays/codexrayupdated this year
X-ray vision for your codebase — semantic knowledge graph & MCP server with 16 tools that saves AI coding agents 30%+ tokens. TF-IDF search, call graphs, impact analysis, dead code detection. Works with Claude Code, Cursor & Windsurf.
npm MIT ★ 8 -
MCP server that scans Azure DevOps work items by area path, flags overdue and stale items, and emails each assignee their own list via Microsoft Graph.
MIT -
GRASP — Code architecture visualizer + 150-tool MCP server. Dependency graphs, security scanning, multimodal knowledge graph, ORM tracking, git change impact, graph schema v3. Works with GitHub, GitLab & local dirs. 35 languages. Zero data collection.
npm NOASSERTION ★ 33 -
MCP server for AI agent work management — persistent work item graph for AI agents
pypi MIT -
Know a Jira work item is ready, then hand its full context to people and AI coding agents. Forge app: Jira panel, readiness board, Rovo agent + skill, MCP server, Teamwork Graph. Codegeist 2026.
MIT -
ckg-mcpgithub.com/yarmoluk/ckg-mcpupdated this year
Context optimization for AI agents — 97 domain knowledge graphs (68 free + 29 Pro), MCP-native traversal. 4× F1 of RAG, 11× fewer tokens per query. Works with Claude, GPT-4o, Gemini, and any MCP client.
pypi MIT -
A transit map of parallel AI agent work: threads and records on a canvas, a git-style branch graph and a timeline. Claude Code hooks, MCP server and skill; no dependencies.
MIT ★ 35 -
MCP Servers for persistent context across work sessions using knowledge graphs
npm ★ 10 -
codemapgithub.com/egentica/codemapupdated this year
A universal suite of MCP-native and node.js API tools for agentic AI, researchers, and developers to map, knowledge-graph, and work with structured code and other artifacts.
npm Apache-2.0 ★ 2 -
Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.
MIT ★ 612 -
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.
pypi MIT ★ 1 -
Persistent memory for each project, dedicated skills, and a shared board for Claude Code and Codex to work together. Code graph, Git history, and a local dashboard. MIT licensed.
MIT -
MCP server that lets coding agents (Claude Code or any MCP client) work autonomously within a session budget — with a dependency graph, human decision queue, required validation and exact handoff. OUTSIDE_MODE for bounded autonomy, DESK_MODE for human-in-the-loop.
MIT -
A context layer for coding agents: notes, RFCs, tasks and tracked time as one graph of plain markdown. The running app hosts an MCP server, so Claude Code and other agents read what is ready, follow the reasoning behind it, and log their own work.
MIT ★ 6 -
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 -
Local graph memory for AI agents. Every answer comes with the path it followed. Stores memories in SQLite, links the people, projects and tools they mention, and combines semantic search with graph traversal. Works as a CLI, MCP server and local web viewer.
MIT ★ 2 -
codegraph is a local-first code context engine and MCP server for repositories. It incrementally indexes source code into a lightweight SQLite graph, then exposes high-signal tools for symbol lookup, call graph traversal, impact analysis, related test discovery, and semantic search. Built in Go with a single-binary workflow, it is designed to work
go NOASSERTION ★ 4 -
Local-first code intelligence over MCP: BM25/FTS5 + AST graph, impact analysis, project memory and safe writes. Text-first by default; optional dense. Works with OpenCode and Zed.
MIT ★ 3 -
Protect customer promises when Jira plans change. RippleGuard connects commitments to Jira work, flags delivery risks, and explains the evidence through Rovo, Teamwork Graph, and read-only MCP tools. Built on Atlassian Forge for Codegeist 2026.
-
🔐 The secrets manager that understands your dependency graph. Maps Issuer → Credential → Project → Deployment → URL. Detects supply-chain risk in npm/Cargo deps. Free, open source, works offline.
AGPL-3.0 -
Portuni is a shared map of how your organization works – its processes, projects, areas, and principles – held as one graph that every tool and every AI agent can read. People and agents draw from the same picture instead of rebuilding context from scratch in every app.
Apache-2.0 ★ 2 -
pandaclipgithub.com/xfloukiex-lab/pandaclipupdated this year
One local-first MCP server for agent working state — clipboard history & snippets, TTL cache, file-organizer overlay, and a knowledge graph — plus a live desktop activity lens. 40 tools, SQLite everywhere, no daemons. Apache-2.0.
Apache-2.0 ★ 6 -
Static code-analysis + knowledge-graph for AI coding agents. Index your codebase once — agents query only what they need. 87–91% token reduction, 12 MCP tools, 13 languages. MCP stdio + HTTP API. Works with Claude Code, Cursor, Antigravity, Codex.
pypi NOASSERTION ★ 1 -
ctx-sysgithub.com/david-franz/ctx-sysupdated this year
Local hybrid RAG over a code knowledge graph. Indexes your codebase with tree-sitter + embeddings + a relationship graph and serves precise context to any AI assistant over MCP — fusing keyword (FTS5), vector, and graph search with reciprocal rank fusion. Local-first via Ollama; works with Claude Code, Cursor, and any MCP client.
MIT ★ 15 -
MCP server for entity SEO: find, rank and compare Google Knowledge Graph entities, audit knowledge panel readiness, map Wikidata connections and generate JSON-LD schema. Works with Claude, Cursor and VS Code.
MIT ★ 2 -
Persistent memory & code intelligence server for AI coding agents. Deploy on VPS for shared memory across machines. Hybrid search (BM25 + pgvector), knowledge graph, impact analysis. 14 MCP tools. Works with Claude Code, OpenCode, Cursor, and any MCP client.
MIT ★ 13 -
A live architecture map of your codebase, on screen beside Claude Code and in the notes your agent reads while it works. Evidence-backed graph with file and line proof, served over MCP and a CLI.
MIT ★ 8 -
Wave-based development lifecycle and code intelligence framework for AI-assisted engineering. Includes semantic + graph indexing, MCP tool surface, built-in secrets detection with lifecycle gates, and a local dashboard for inspecting project health, active work, and diffs.
Apache-2.0 ★ 6 -
Oh-my-ClaudeClawgithub.com/Kit4Some/Oh-my-ClaudeClawupdated this year
Autonomous AI assistant plugin for Claude Code — 5 MCP servers, 21 skills, 3-tier persistent memory, knowledge graph, multi-agent orchestration with Discord/Telegram integration for 24/7 Everyday working
MIT ★ 4 -
Dragon Brain — persistent long-term memory for AI agents via MCP (Model Context Protocol). Knowledge graph (FalkorDB) + vector search (Qdrant) + CUDA GPU embeddings. Works with Claude, Gemini CLI, Cursor, Windsurf, VS Code Copilot. 30 tools, 1121 tests.
MIT ★ 51 -
MCP server for AI coding agents. Instead of reading files one by one, your agent gets dependency graphs, git intent, blast radius, and change health in a single call. Works with any language deep analysis for TypeScript,Java, Go, and C#.
npm MIT ★ 74 -
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 -
eidetic-memorygithub.com/rongshenCarson/eidetic-memoryupdated this year
Eidetic — a single-process, single-database memory server for AI agents. SQLite-native: vectors + FTS5 + knowledge graph + raw logs. Five-layer memory (L0 raw → L1–L4), three-tier recall, auto-healing. One-command deploy, local-first, works with any MCP-compatible agent (OpenClaw, Claude Code, etc.).
pypi Apache-2.0 -
hcegithub.com/nakurian/hceupdated this year
Middleware memory engine for LLMs — replaces linear chat history with three parallel structures (Entity Graph, Semantic Tree, Focus Buffer) to retrieve only the most relevant context within a token budget. Works as a Python library or MCP server for Claude Code, Copilot CLI, and other AI tools.
★ 2 -
A block-graph store for LLM agents and the people working with them, with its daemon and MCP shell.
npm Apache-2.0 -
Two MCP stdio servers in .NET 10: Microsoft Teams (teams, channels, chats, messages, search) via Microsoft Graph, and Azure DevOps (work items, pull requests, pipelines, repos, search) via its REST API. Interactive Entra ID sign-in instead of PATs; read-only by default with opt-in write and send gates.
nuget MIT -
clauderizergithub.com/collincusce/clauderizerupdated this year
Drop-in, MCP-native working memory for AI agents: gameplans, phases, a dependency graph, and post-hoc cascade — over plain markdown.
pypi Apache-2.0 -
FYOS hub plugins for operations: situation picture, cluster control desk, repos, Kubernetes, work, git, TrueNAS, Omada, pipelines, operations graph (Apache-2.0)
Apache-2.0 ★ 1 -
universal-memory-mcpgithub.com/JasonMakes801/universal-memory-mcpupdated this year
Universal Memory MCP server — persistent knowledge graph for AI assistants. Works with Claude, ChatGPT, Gemini, Cursor, VS Code, and any MCP-compatible client. Built on Cloudflare Workers.
★ 1 -
Forge app for Jira and Confluence: catches work that contradicts team decisions, with a Rovo agent, MCP server and Teamwork Graph blast radius. Codegeist 2026.
MIT -
mcp-package-healthgithub.com/fse08877-netizen/mcp-package-healthupdated this year
MCP server for real-time package health, vulnerability scanning & dependency graphs — works inside Claude, Cursor, and any MCP-compatible client.
MIT