there (Session, ContextManager, tool calling)
- Handy for quick testing a prompt or a local MCPserver without writing a client
- Should not dominate README real-estate; a short Quick Start
6.6k4mo agoReviewMountCreate a free account to mount
applicable skills with `warden --skill `.
-
## Multi-process filesystem state
- MobileBuildMCP explicitly supports multiple concurrent MCPserver, daemon, CLI, test, and helper processes for the same or different workspaces.
- Shared filesystem
6.5k50d agoReviewMountCreate a free account to mount
teach AI assistants how to build flawless n8n workflows using the n8n-mcpMCPserver.
**Repository**: https://github.com/czlonkowski/n8n-skills
**Purpose**: 14 complementary skills that provide expert guidance on using
No other project uses it yet
6.5k3mo agoReviewMountCreate a free account to mount
when working with code in this repository.
## Project Overview
**Gemini Notebook (formerly Google NotebookLM) MCPServer & CLI** - Provides programmatic access to Gemini Notebook (notebook.google.com) via both a Model Context Protocol
6.5k8d agoReviewMountCreate a free account to mount
sets `output: 'standalone'`
## Agent Control Interfaces
Mission Control provides three interfaces for autonomous agents:
### MCPServer (recommended for agents)
```bash
# Add to any Claude Code agent:
claude mcp add mission
6.4k4mo agoReviewMountCreate a free account to mount
claude-haiku-4-5"}`.
The Claude Code CLI, and every tool, hook and stdio MCPserver it runs, inherits the
server's environment, including the values passed with `--secrets`. Give
Steady2 mentions in 2 weeks
No other project uses it yet
6.3k17d agoReviewMountCreate a free account to mount
Codex plugin (`.codex-plugin/plugin.json`). `remove-ai-watermarks mcp` is a standard-library MCPserver that runs one CLI command per tool call; keep it dependency-free, because the MCP
No other project uses it yet
6.3k17d agoReviewMountCreate a free account to mount
/docs/derived_objects/ARCHITECTURE.md), recording and source cache in [RECORDING_AND_CACHING.md](./docs/RECORDING_AND_CACHING.md) and [session_recorder_design.md](./docs/session_recorder_design.md), AI agents over MCP (server, bridge, plugin endpoint) in [MCP_SERVER.md](./docs/MCP_SERVER.md). [docs/archive/](./docs/archive) holds retired plans (history only
6.3k19d agoReviewMountCreate a free account to mount
runtime`'s `DerivedObjects`; `MainWindow` keeps thin wrappers and owns only what is UI.
- **MCPserver (`src/mcp/`, desktop only).** One server per window, started on first need and destroyed in `~MainWindow
6.3k19d agoReviewMountCreate a free account to mount
relicense them.
- `tool_registry.hpp`, `tool_context.hpp`: the tool catalog and no-throw dispatch the MCPserver serves; the `ToolContext` of host views is built per call on the GUI thread
6.3k19d agoReviewMountCreate a free account to mount
with websites. It leverages Schema.org markup and supports MCP (Model Context Protocol) for AI agent interactions.
## Common Development Commands
### Running the Server
```bash
# Start aiohttp server (recommended)
./startup_aiohttp.sh
# Or directly
6.3k8mo agoReviewMountCreate a free account to mount
with `maildev --mcp` (endpoint at
`http://localhost:1080/mcp`), or run the standalone stdio server via `maildev-mcp`
for Claude Desktop.
---
**License:** MIT
**Maintained by:** MailDev Contributors
6.1k4mo agoReviewMountCreate a free account to mount
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.