AI agents use git_lfs 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.
The git_lfs tool modifies repository state by adding or removing file patterns from LFS tracking, which changes how files are stored and handled. This is a Write operation (reversible configuration change) rather than Execute or Destructive, since tracking changes can be undone.
From the tool's definition Tool name 'git_lfs' with description stating it 'Manage Git Large File Storage (LFS). Supports tracking/untracking file patterns' indicates creation and modification of LFS configuration and tracked file patterns.
Attacks that exploit this kind of access
Manage Git Large File Storage (LFS). Supports tracking/untracking file patterns,. 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_lfs: 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_lfs 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_lfs 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_lfs. 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_lfs 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 →