AI agents use staged_write 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 data in a staged git session, which is reversible via git operations (abort_staged, finalize_staged). It does not irreversibly delete data (would be Destructive), execute arbitrary code (Execute), or move money (Financial). The blast radius is medium because an agent could modify sensitive files, but changes remain staged and can be reviewed or aborted before finalization.
From the tool's definition Tool name 'staged_write' and description 'Write to a staged session' indicate data modification. The server context shows this integrates git with filesystem operations and 'enforces commits on writes,' meaning changes are staged (reversible) rather than…
Attacks that exploit this kind of access
Write to a staged session. 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 staged_write: 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.
staged_write 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 staged_write 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 staged_write. 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.
staged_write 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 →