Find and replace text in a file
AI agents use replace_in_file to create or update resources in MCP Start App — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Start App environment.
The tool modifies file content through text replacement, a reversible operation. While it changes data, the changes can be undone (via get_edit_history and get_file_diff visible on this server, or standard version control). This is Write rather than Destructive because the operation is not irreversible—file content can be restored.
From the tool's definition Tool description states 'Find and replace text in a file', which modifies file content. Combined with sibling tools like 'delete_lines' and 'edit_file_lines', this is clearly a Write operation that creates or modifies data reversibly.
Attacks that exploit this kind of access
Find and replace text in a file. It is categorised as a Write tool in the MCP Start App MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Start App MCP server in PolicyLayer and add a rule for replace_in_file: 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 MCP Start App. Nothing to install.
replace_in_file 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 replace_in_file 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 replace_in_file. 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.
replace_in_file is provided by the MCP Start App MCP server (nexus-aissam/mcp-local). 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 →