Medium Risk

write_content

Write or append content to multiple specified files (creating directories if needed). NOTE: For modifying existing files, prefer using

How to control write_content ↓

What write_content does on Filesystem

AI agents use write_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.

Medium Risk

Why write_content needs a policy

The tool creates or modifies files reversibly—writes can be overwritten or reverted. While high severity due to potential for overwriting important files or creating malicious content, it does not irreversibly destroy data (Destructive) or execute arbitrary code (Execute). The ability to affect multiple files simultaneously elevates severity from medium to high.

From the tool's definition Tool name: write_content; description states 'Write or append content to multiple specified files (creating directories if needed)'. The description explicitly mentions the ability to modify existing files.

Documented attack patterns abuse exactly the kind of access write_content gives an agent:

How to control write_content

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 write_content:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "write_content": {
      "limits": [
        {
          "counter": "write_content_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

write_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.

  1. Create a free account and register Filesystem — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about write_content

What does the write_content tool do? +

Write or append content to multiple specified files (creating directories if needed). NOTE: For modifying existing files, prefer using. 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.

How do I enforce a policy on write_content? +

Register the Filesystem MCP server in PolicyLayer and add a rule for write_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.

What risk level is write_content? +

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

Can I rate-limit write_content? +

Yes. Add a rate_limit block to the write_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.

How do I block write_content completely? +

Set action: deny in the PolicyLayer policy for write_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.

What MCP server provides write_content? +

write_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.

Enforce policy on every Filesystem tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.