Provides read-only inspection of Git worktree topology, offering aggregate signals about worktree counts, cleanliness, and states such as detached, locked, or prunable.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@worktree-orbit-mcp What's the status of all worktrees in this repo?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Worktree Orbit is a local MCP for developers who keep several Git worktrees alive at once. It answers whether a repository has parallel worktrees, whether they are clean, and whether detached, locked, or prunable worktrees need attention.
inspect_worktree_topology: returns aggregate worktree count, primary and linked counts, clean or dirty counts, detached state, lock state, prunable state, and a coarse topology hint.
It never returns paths, branch names, hashes, remotes, lock reasons, subjects, authors, or file contents.
Related MCP server: Repository Inspector
Local Git commands only. No network access is used.
The selected repository must stay inside WORKTREE_ORBIT_ROOT.
Commands are read-only: the server does not add, remove, move, lock, unlock, reset, prune, or modify worktrees.
Worktree status checks are bounded and time limited.
Results are aggregate signals, not a replacement for inspecting a specific worktree before deleting it.
npm install
npm run build
node dist/index.jsSummarize local Git worktree topology, clean or dirty state, detached worktrees, locks, and prunable entries without exposing paths, branch names, hashes, remotes, or content.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | Local Git repository path; no network access is used. | . |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses key behavioral traits: it only summarizes (read-only) and intentionally avoids exposing specific Git details. It also implies local-only operation via the cwd parameter description. However, it does not mention output format, error behavior, or explicit non-mutation, so it is not fully transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-organized sentence that front-loads the primary action and then lists constraints and exclusions. No redundant information; every clause adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With one parameter, no annotations, and no output schema, the description adequately conveys the tool's scope and safety characteristics. It could mention the return format or that the operation is non-mutating, but the current text covers the core purpose and constraints sufficiently for a simple read-only summarization tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage for the only parameter (cwd) is 100%, so the schema already documents that it is a local Git repository path. The description reinforces 'local' and adds a no-network-access detail, but this is minimal added meaning beyond the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool summarizes local Git worktree topology and enumerates specific aspects (clean/dirty state, detached worktrees, locks, prunable entries). It also explicitly lists what it does not expose (paths, branch names, hashes, remotes, content), which fully distinguishes its purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context: it is for safe, local-only inspection without leaking sensitive information. However, it does not explicitly name alternatives or provide when-not-to-use guidance, which prevents a 5 since there are no sibling tools to differentiate against.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0inspect_worktree_topologyWith only one tool, there is no possibility of confusion or overlap between tools. The tool's purpose is clearly described, making selection unambiguous.
The tool name 'inspect_worktree_topology' follows a clear verb_noun pattern in snake_case, which is consistent and predictable. As a single tool, it sets a clear convention.
The server has only one tool, which is on the low end of typical tool counts. While the narrow scope of inspection might justify a single tool, the server name suggests a broader worktree management capability, making the count feel slightly thin.
The tool provides a comprehensive inspection summary, but lacks any management operations (create, delete, prune, etc.) that the server name 'worktree-orbit' implies. This leaves significant gaps in the tool surface for full worktree lifecycle coverage.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Screens public GitHub repos and PRs to generate risk maps, findings, and merge-readiness signals.
Read-only MCP access to a documented IT fleet: state, changes, posture. 15 tools.
Generate SBOMs, scan vulnerabilities, and analyze dependencies from local projects or Git repos.
Run verified read-only code tools: quant diagnostics + agent-ops preflight, no source exposure.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mrfentmen/worktree-orbit-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
