Stage files for commit
AI agents use git_add to create or update resources in MCP Git Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Git Server environment.
git_add stages files for inclusion in the next commit, modifying Git's index. This is reversible (files can be unstaged with git_reset), making it Write rather than Destructive. The severity is medium because misuse could stage unintended files before committing sensitive data, but the operation itself is easily undone and has limited blast radius compared to commit or push operations.
From the tool's definition Tool name is 'git_add' and description states 'Stage files for commit'. This modifies the Git index/staging area by adding file changes, which is a reversible operation typical of Write category tools.
Attacks that exploit this kind of access
Stage files for commit. It is categorised as a Write tool in the MCP Git Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Git Server 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 MCP Git Server. 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 MCP Git Server MCP server (mikeybeez/mcp-git). 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 →