Model Context Protocol. It ends "both sides" of the protocol—`mcp_server()` launches an MCPserver, and `mcp_tools()` implements the client side. `mcp_session()` is an optional extension
Plugin** (`gimp-mcp-plugin.py`): A GIMP 3.2 plugin that starts a socket server inside GIMP
2. **MCPServer** (`gimp-mcp-server.py`): An MCPserver that connects to the GIMP plugin and exposes GIMP functionality
Code (claude.ai/code) when working with code in this repository.
## Project Overview
StarRocks Official MCPServer - A bridge between AI assistants and StarRocks databases, built using FastMCP framework. Enables direct
Project instructions moved to [AGENTS.md](AGENTS.md), the canonical Codex operating guide.
The server is a Bun/TypeScript MCP integration for Raindrop.io with STDIO and Streamable HTTP entry points. Keep this file
Model Context Protocol) plugin for iOS development automation. It provides 8 modular, workflow-specific MCPservers that consolidate 23 iOS operations across build, test, simulator control, and UI automation.
**Status
data sources (government databases, international organizations, academic datasets, etc.).
The project exposes a hosted MCPServer at `https://firstdata.deepminer.com.cn/mcp`.
## Validation
Dependencies are managed with [uv](https://docs.astral.sh/uv/).
regardless of `.toe` save state.
### Envoy MCP Architecture
Dual-thread design: worker thread runs MCPserver (no TD imports), main thread executes TD operations via `_onRefresh()`. Communication via `threading.Event` + `Queue
source of truth, git is the changelog.
**Tech stack**: Rust CLI binary with integrated MCPserver (`markplane mcp` subcommand) wrapping a shared core library. React + Tailwind web UI via `markplane
during `migrate` on a fresh DB (issue #15/#16) and avoids excessive DB connections.
### MCPServer (`orbit/mcp_server.py`, `orbit/management/commands/orbit_mcp.py`)
`create_mcp_server()` builds a `FastMCP` instance (from the optional `mcp
Documentation for Claude
## Project Overview
macOS-MCP is a lightweight, open-source MCP (Model Context Protocol) server that enables AI agents to seamlessly integrate with and automate macOS through
call the API or per-domain MCP tools directly. They go through two thin MCPservers (`roboco-flow` for intent verbs, `roboco-do` for content tools) backed by the server
skills/ # Skills (in plugin.json)
│ └── oh-my-claude-runtime/ # Runtime workflow guidance skill
└── .mcp.json # Plugin MCPservers
```
Plugin-root `CLAUDE.md` is not loaded as runtime context by current Claude Code. Ship
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.