AI agents use write_and_commit 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 creates or modifies files and commits them to git, which is reversible. It does not delete data (would be Destructive) or execute arbitrary code (would be Execute). However, it carries high severity because an AI agent could write malicious code, overwrite critical files, or corrupt repository history if misused.
From the tool's definition Tool description states 'Write a file and create an atomic git commit with templated message.' The primary action is writing/modifying file content, with git commit as a side effect. This is reversible through git operations (revert, reset).
Attacks that exploit this kind of access
Write a file and create an atomic git commit with templated message. 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 write_and_commit: 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.
write_and_commit 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 write_and_commit 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 write_and_commit. 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.
write_and_commit 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 →