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.
-
lossless-codegithub.com/GodsBoy/lossless-codeupdated this year
DAG-based Lossless Context Management for Claude Code. Every message preserved, summaries cascade as a DAG, patterns extracted via Lossless Dream — full recall and reflection across sessions.
MIT ★ 15 -
TasksMultiServergithub.com/keyurgolani/TasksMultiServerupdated this year
✅ Multi-interface hierarchical task management (Projects → Lists → Tasks) for humans and AI agents — MCP server, REST API, and React web UI. DAG task dependencies, pluggable PostgreSQL/filesystem storage. FastAPI + React.
MIT -
pondergithub.com/nick-dorsch/ponderupdated this year
DAG based task management system, with MCP bindings for agentic coding workflows
-
Local-first MCP task manager & real-time Web UI for AI coding agents (Claude Code, Cursor, Windsurf, Antigravity) with DAG workflows, proof verification, and ADR sync.
npm MIT ★ 3 -
Model Context Protocol server for Apache Airflow - enables AI assistants to interact with Airflow workflows, monitor DAG runs, and manage tasks programmatically
MIT -
MCP server for multi-terminal Claude Code orchestration with DAG task management, parallel execution, and self-improvement
npm MIT -
ChatGPT Ads MCP Server & Agent Skill for OpenAI Ads Manager Beta: Context Hints, Delta Feeds, CAPI oppref tracking & Bulk DAG automation
MIT -
airflow-mcpstale
本项目是一个与 Apache Airflow 集成的 Model Context Protocol (MCP) 服务器,提供多种工具来管理和监控 Airflow 的 DAG 运行。它支持触发 DAG、获取 DAG 状态、回填数据、获取日志等操作。
pypi MIT -
Task chain management engine for AI agents with MCP integration
pypi Proprietary -
🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.
npm MIT ★ 3 -
Plain-text issue tracking in orgmode files, with a CLI and an MCP server
cargo MIT ★ 1 -
@synsci/thesisgithub.com/synthetic-sciences/thesisupdated this year
Thesis by Synthetic Sciences — graph-based research management. One-command MCP setup.
npm MIT -
ShadowEdge — single-binary red-team collaboration: asset center, 11-phase board, DAG attack paths, finding lifecycle, MCP, master/edge sync. 单文件红队协同平台:资产中心、11 阶段作战板、DAG 攻击路径、漏洞生命周期、MCP 与主从同步。
MIT ★ 1 -
Control Apache Airflow with natural language via MCP. Chat with your workflows using Claude, GPT, or any LLM — no REST API calls needed. Supports Airflow 2.x (43 tools) & 3.0+ (45+ tools).
MIT ★ 54 -
Project-scoped task board for coordinating multiple AI agents: CLI-first, SQLite-backed, with a read-only board and dependency-DAG view. MCP is supported
MIT