Replace content within files across multiple specified paths.
AI agents use replace_content to create or update resources in Filesystem — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Filesystem environment.
This tool modifies file content reversibly without deletion. It is Write rather than Destructive because replacement is theoretically reversible (original content could be recovered from backups or version control).
From the tool's definition Tool name 'replace_content' and description 'Replace content within files across multiple specified paths' indicates modification of file content.
Documented attack patterns abuse exactly the kind of access replace_content gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Filesystem, and nothing reaches the server without passing your rules. This is the rule we recommend for replace_content:
{
"version": "1",
"default": "deny",
"tools": {
"replace_content": {
"limits": [
{
"counter": "replace_content_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}replace_content stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Replace content within files across multiple specified paths. It is categorised as a Write tool in the Filesystem MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Filesystem MCP server in PolicyLayer and add a rule for replace_content: 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 Filesystem. Nothing to install.
replace_content 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_content 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_content. 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_content is provided by the Filesystem MCP server (sylphxai/filesystem-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Filesystem, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 Filesystem tools catalogued and risk-classified — across an index of 43,000+ MCP servers.