AI agents use apply_diff 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.
Applying diffs modifies file contents in a targeted, reversible manner. While high-risk due to potential unintended file corruption or logic injection if an AI agent applies malicious patches, this is a Write operation rather than Destructive because diffs are typically reversible through counter-diffs or version control.
From the tool's definition Tool name 'apply_diff' combined with description 'Apply diffs to files' indicates modification of file contents. The sibling tools include 'delete_items' and 'replace_content', confirming this server handles file mutations.
Documented attack patterns abuse exactly the kind of access apply_diff 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 apply_diff:
{
"version": "1",
"default": "deny",
"tools": {
"apply_diff": {
"limits": [
{
"counter": "apply_diff_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}apply_diff 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.
Apply diffs to files. 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 apply_diff: 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.
apply_diff 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 apply_diff 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 apply_diff. 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.
apply_diff 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.