AI agents use apply_patch_and_commit_func to create or update resources in Fs Git — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Fs Git environment.
This tool applies patches (modifying file content) and commits changes, which are reversible write operations. While patches can affect multiple files, commits are part of git history and can be reverted. It does not delete data irreversibly (Destructive), execute arbitrary code (Execute), or move money (Financial).
From the tool's definition Tool name 'apply_patch_and_commit_func' and description 'Apply patch and commit' indicate it modifies files via patch application and creates a git commit.
Attacks that exploit this kind of access
Apply patch and commit. It is categorised as a Write tool in the Fs Git MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fs Git MCP server in PolicyLayer and add a rule for apply_patch_and_commit_func: 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 Fs Git. Nothing to install.
apply_patch_and_commit_func 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 apply_patch_and_commit_func 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 apply_patch_and_commit_func. 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.
apply_patch_and_commit_func is provided by the Fs Git MCP server (wojons/fs-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 →