AI agents invoke git_bisect to trigger actions in Git. 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.
git_bisect is an Execute risk because it automates sequential operations (checkout commits, run tests, mark commits as good/bad) whose side effects depend on the repository state and test outcomes. While not destructive itself, bisect can trigger arbitrary test scripts and leave the repository in intermediate states.
From the tool's definition Tool runs 'bisect workflows for bug isolation' — a complex Git operation that executes automated testing and state transitions across commits without reversibility constraints. The description explicitly states 'run', indicating active execution.
Attacks that exploit this kind of access
Run bisect workflows for bug isolation. It is categorised as a Execute tool in the Git MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Git MCP server in PolicyLayer and add a rule for git_bisect: 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 Git. Nothing to install.
git_bisect 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 git_bisect 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 git_bisect. 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.
git_bisect is provided by the Git MCP server (selfagency/git-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →