fs_apply_diff

A write tool on the Container- MCP server.

SERVERContainer-MCP SOURCE54rt1n/container-mcp

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/54rt1n-container-mcp/fs-apply-diff.md

WHAT IT DOES

What fs_apply_diff does on Container-MCP

AI agents use fs_apply_diff to create or update resources in Container-MCP, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Container-MCP environment.

RISK

Why fs_apply_diff is rated Medium

The tool modifies files by applying diffs—a reversible write operation. While diffs can theoretically delete content, without explicit description indicating irreversible destruction (unlike fs_delete), it is classified as Write. Severity is high because unvetted diff application could corrupt critical files or introduce malicious code into the system.

From the tool's definition Tool name 'fs_apply_diff' indicates application of filesystem diffs/patches. Sibling tools include fs_read, fs_write, fs_delete, fs_move, confirming filesystem manipulation context. Description is empty, limiting specificity.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs fs_apply_diff safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Container-MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fs_apply_diff, this is the rule to start with:

fs_apply_diff Rate-limited

fs_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "fs_apply_diff": {
      "limits": [
        {
          "counter": "fs_apply_diff_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Container-MCP, apply this rule, and every fs_apply_diff call is checked against it from then on.

FAQ

Questions about fs_apply_diff

What does the fs_apply_diff tool do? +

fs_apply_diff is a write tool on the Container MCP server. It is categorised as a Write tool in the Container-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on fs_apply_diff? +

Register the Container MCP server in PolicyLayer and add a rule for fs_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 Container-MCP. Nothing to install.

What risk level is fs_apply_diff? +

fs_apply_diff is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit fs_apply_diff? +

Yes. Add a rate_limit block to the fs_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.

How do I block fs_apply_diff completely? +

Set action: deny in the PolicyLayer policy for fs_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.

What MCP server provides fs_apply_diff? +

fs_apply_diff is provided by the Container MCP server (54rt1n/container-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Container, and thousands of servers like it.

This server

All 27 Container tools →

Across the catalogue

binary_patch_apply on 010 Editor → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →