arbor
Run agentic coding workflows in a fully native desktop app for Git worktrees, terminals, and diffs.
Arbor MCP server provides programmatic access to a native Git worktree and terminal management daemon through the Model Context Protocol. Built in Rust, the arbor-mcp binary exposes structured tools for creating and managing worktrees, running terminals, controlling processes, and tracking AI agent activity across repositories. The MCP server connects to arbor-httpd, a persistent daemon that backs both the desktop app and remote operations, enabling AI assistants to orchestrate parallel coding sessions and issue-driven workflows.
Key Features
Use Cases
- 01Enabling AI assistants to create isolated worktrees for each GitHub issue or feature branch
- 02Orchestrating terminal commands across multiple repositories from a chat interface
- 03Managing long-running development processes and scheduled tasks through AI agent workflows
- 04Accessing remote development environments and worktrees over authenticated HTTP connections
- 05Tracking and coordinating multiple concurrent AI coding agent sessions in separate branches
- 06Automating repository setup, process restart, and cleanup tasks via MCP tool calls
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
arbor — FAQ
What is the Arbor MCP server?+
Arbor MCP server is a stdio-based Model Context Protocol implementation that connects AI assistants to a persistent daemon managing Git worktrees, terminals, processes, and tasks. It exposes tools for repository and worktree management, terminal sessions, and agent activity tracking.
How do I install and configure the Arbor MCP server?+
Download the arbor-mcp binary from GitHub releases or build from source with cargo build -p arbor-mcp. Start the arbor-httpd daemon first, then add arbor-mcp to your MCP client config with the command path and optional ARBOR_DAEMON_URL environment variable.
Which AI clients work with Arbor MCP server?+
Arbor MCP server works with any client supporting the Model Context Protocol stdio transport, including Claude Desktop, Cline, and other MCP-compatible tools. The daemon must be running locally or accessible remotely before the MCP server connects.
Does Arbor MCP server require API keys or authentication?+
Loopback connections require no authentication. For remote daemon access, set an auth_token in ~/.config/arbor/config.toml on the daemon host and pass it via ARBOR_DAEMON_AUTH_TOKEN when running arbor-mcp.
Is Arbor MCP server free and open source?+
Yes, Arbor is released under the MIT license and available as open source on GitHub. All binaries including arbor-mcp are built from the same monorepo and distributed together.
What are the prerequisites for running Arbor MCP server?+
You need the arbor-httpd daemon running and reachable at the configured URL (default http://127.0.0.1:8787). The daemon requires Rust nightly-2025-11-30 to build from source, or you can use prebuilt release binaries for macOS, Linux, or Windows.
How do I install arbor?+
Open the source repository on GitHub and follow its README. arbor is a mcp server — MCP Agents Market links you directly to the official repo.
Is arbor free?+
arbor is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.