AI agents use fs_replace to create or update resources in Emcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Emcp environment.
fs_replace most likely creates or modifies file contents reversibly, classifying as Write rather than Destructive (which would require permanent deletion/overwrite without recovery). The lack of a description lowers confidence slightly, but the tool name and server context strongly suggest file modification semantics.
From the tool's definition Tool name 'fs_replace' indicates file replacement/modification. Server description confirms 'filesystem operations' capability. No description provided, but naming convention parallels other filesystem tools (fs_read, fs_write, fs_rm) that modify files.
Attacks that exploit this kind of access
fs_replace. It is categorised as a Write tool in the Emcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the E MCP server in PolicyLayer and add a rule for fs_replace: 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 Emcp. Nothing to install.
fs_replace 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 fs_replace 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 fs_replace. 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.
fs_replace is provided by the E MCP server (slezica/emcp). 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 →