This record as markdown: /tools/io-github-dave-london-go/worktree.md
What worktree does on Go
AI agents invoke worktree to trigger actions in Go. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why worktree is rated High
This tool performs multiple operations on git worktrees. While 'list' is a read operation, 'add', 'remove', 'prune', 'lock', and 'unlock' are write/execute/destructive operations. 'Remove' and 'prune' can irreversibly delete worktrees. Per the most-severe-wins rule, the destructive capability should be considered, but worktree removal is somewhat recoverable (the branch/commits still exist).
From the tool's definition Lists, adds, removes, locks, unlocks, or prunes git worktrees for managing multiple working trees
Attacks that exploit this kind of access
The rule that runs worktree safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Go, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For worktree, this is the rule to start with:
worktree stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Go, apply this rule, and every worktree call is checked against it from then on.
Questions about worktree
Lists, adds, removes, locks, unlocks, or prunes git worktrees for managing multiple working trees. Returns structured data with worktree paths, branches, and HEAD commits. It is categorised as a Execute tool in the Go MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Go MCP server in PolicyLayer and add a rule for worktree: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Go. Nothing to install.
worktree is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the worktree rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for worktree. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
worktree is provided by the Go MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Go, and thousands of servers like it.
This server
Across the catalogue