AI agents invoke git_workflow 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.
This is Execute rather than Write because it executes multi-step workflows whose side effects are not simply 'create or modify data reversibly' but depend on arbitrary workflow logic. While individual workflow steps might be Write operations (commits, pushes), the tool itself runs/executes them.
From the tool's definition Tool description states 'Run named multi-step Git workflows' — the verb 'Run' indicates execution of potentially complex, multi-step operations.
Attacks that exploit this kind of access
Run named multi-step Git workflows with resumable lifecycle controls. 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_workflow: 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_workflow 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_workflow 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_workflow. 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_workflow 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 →