MCP server

Let Claude Code and other agents drive Tegment over MCP.

Last updated Nov 03, 2026

Tegment runs a local Model Context Protocol server that lets an MCP-aware agent (Claude Code, Gemini CLI, OpenCode, Antigravity CLI, and others) read your projects, worktrees, and issues, and start and tail your apps. It's how an agent working in a Tegment terminal can act on the rest of the app.

How it works#

Tegment runs a small local server on your machine while it's open. It listens on localhost only, with nothing exposed to the network, so your agents can reach it but nothing outside your machine can.

Agents connect through a helper that Tegment bundles, rather than talking to the server directly. If you run more than one Tegment window, an agent started in a terminal automatically reaches the window it belongs to.

Set it up#

Open Settings → Agents. Every agent has one card there, saying whether Tegment found it on this machine and whether it is set up, and a Set up button that registers the Tegment server for you. A card reading Partly set up tells you which half is missing and what you lose without it. (For the full per-agent picture, see Supported agents.)

If an agent you have turned on is only partly set up, Tegment tells you when it starts, with a button that takes you to the agent settings.

Claude Code: installing the Tegment plugin wires up the MCP server. The Set up button is the fallback if you don't use the plugin (it runs claude mcp add … tegment … mcp).
OpenCode, Gemini CLI, Codex, Cursor, and Antigravity CLI: one click on Set up writes the Tegment server into the agent's own config for you.
Other MCP clients: there's no auto-setup, so add it by hand. Point the client at the bundled tegment binary with the mcp argument; the Manual setup block at the bottom of the page shows the exact path.

Tools#

The server exposes a flat set of tools. There is no per-agent permission model, so a configured agent can use all of them.

Tegment knows which terminal a call comes from, so an agent never has to pass ids for its own terminal or worktree. Tools that take a project fall back to the project the agent runs in.

Tool	What it does
`list_projects`	List all projects registered in Tegment.
`get_project_info`	Detailed info for a project: IDE, GitHub/Jira links, build & run configs, worktrees.
`list_worktrees`	List a project's worktrees.
`get_context`	Return the project and worktree the calling agent runs in.
`list_issues`	List GitHub and Jira issues for a project. By default each issue carries its headline fields (key, title, status, type, priority, assignee, parent, last updated); ask for `full` to get every field.
`get_issue`	Fetch a single GitHub or Jira issue in full: description, parent epic, sub-tasks, linked issues and what each link means, and the newest comments.
`list_app_configs`	List a project's build & run configs.
`start_app` / `stop_app`	Start a build & run config in the agent's own worktree, or stop it.
`get_app_status`	Report which apps are running in the agent's worktree.
`get_app_output`	Return recent log lines from a running app.
`notify`	Show a notification on the agent's tab in Tegment.
`request_review`	Say that the work on a ticket is done and committed, and ready for AI review.
`submit_review`	Hand in a review: the findings, one by one or as Markdown, and a verdict. Used by the reviewer.