AI agents use git_add to create or update resources in Git — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Git environment.
git_add modifies Git's internal state (the index) by staging file changes, but does not create permanent commits or alter the repository history. It is reversible via git reset or similar commands. This qualifies as Write rather than Execute because it is a data modification operation with well-defined semantics, not arbitrary command execution.
From the tool's definition Tool name is 'git_add' and description states it will 'Stage files in the index.' Staging files modifies the Git index/staging area, preparing them for commit. This is a reversible operation (files can be unstaged with git reset).
Attacks that exploit this kind of access
Stage files in the index. It is categorised as a Write tool in the Git MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Git MCP server in PolicyLayer and add a rule for git_add: 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_add is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the git_add 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_add. 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_add 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 →