Open Source MCP Projects
The Model Context Protocol (MCP) is an open standard for connecting AI applications to external tools, data sources, and services through a consistent interface. It helps reduce the need for custom integrations between each assistant and each system, making it easier to expose capabilities such as search, file access, and task execution while keeping communication structured.
164 repositories · updated October 15, 2026
open-timeline-engine: Shared Memory for AI Agents via MCP
Open Timeline Engine is a local-first Python context engine for MCP-compatible agents such as Claude, Codex, and Cursor. It captures work over time, finds recurring patterns, and returns past decisions with citations and safety gates.
rag-agent-platform: Self-Host RAG Agents and MCP Tools
A self-hosted Java and Next.js platform for combining document retrieval, LLM-powered agents, and MCP tools. It suits teams that want a configurable knowledge and agent workflow under their own infrastructure, with external services to operate.
ActiveHealth 32/100
ContextTax: Measure MCP Tool Costs in an AI Context Window
ContextTax is a cross-platform CLI that measures how much MCP tool schemas and responses consume from an AI agent’s context window. Use Anthropic token counting for ground-truth figures or an offline estimate when you do not have an API key.
QuietHealth 20/100
Koshi: Give AI Coding Agents Local Memory and Retrieval
Koshi is a local-first MCP server for giving AI coding agents durable project memory, code retrieval, and shared team decisions. It suits teams that want context to persist across sessions and machines without relying on cloud services or API keys.
QuietHealth 24/100
plur: Share Persistent Memory Across AI Agents
PLUR gives AI agents a shared, local-first memory store of readable YAML files. It suits developers who want corrections and project conventions to carry across sessions and tools without relying on a hosted memory service.
ActiveHealth 75/100
seclab-taskflow-agent: Define AI Workflows in YAML
A Python framework and CLI for building multi-agent workflows from YAML, with MCP tools and configurable model backends. It is aimed at security research, code auditing, and other repeatable agent tasks.
ActiveHealth 45/100
open-codex-computer-use: Automate Desktop Interfaces Through MCP
open-codex-computer-use exposes desktop automation as an MCP service that AI agents and compatible clients can use on macOS, Linux, and Windows. It is useful when an agent needs to interact with desktop apps through accessibility-based controls.
NewHealth 57/100
OrcaReplay: Record and Replay AI Agent Runs
OrcaReplay records AI agent runs so developers can inspect what happened, replay interactions offline, and fork a run from a checkpoint onto another model. It is a TypeScript CLI for debugging and comparing agent behavior without modifying the agent.
NewHealth 62/100
SwarmLLM: Run Local and Distributed AI Models
SwarmLLM runs open AI models on your computer and can pool resources with other computers to run larger models. It also provides OpenAI- and Anthropic-compatible APIs for local apps and agents.
ActiveHealth 46/100
openmake_llm: Coordinate AI Models, Agents, and Tools
OpenMake is a self-hosted AI workspace that coordinates chat models, agents, and tools in one place. It suits people who want multi-step AI workflows with local or open-weight models, while keeping infrastructure and model choices under their control.
ActiveHealth 56/100
zennotes: Manage Markdown Notes with Keyboard-First Tools
ZenNotes is a local-first Markdown notes app for people who prefer plain files, keyboard navigation, and Vim motions. It runs as an Electron desktop app or a self-hosted web app, with search, diagrams, CLI, and MCP integrations.
NewHealth 70/100
ai-session-search: Search Local AI Coding Sessions
ai-session-search indexes local transcripts from multiple AI coding tools and lets you search sessions, messages, and edited files. Use it from a Rust-powered CLI, MCP server, Rust library, or Python API.
ActiveHealth 39/100