Medium Risk

write_file

Create a new file or completely overwrite an existing file with new content. Use with caution as it will overwrite existing files without warning. Handles text content with proper encoding. Only works within allowed directories.

Part of the Filesystem server.

write_file can modify Filesystem data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE FILESYSTEM →

Free to start. No card required.

AI agents use write_file to create or modify resources in Filesystem. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call write_file repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Filesystem.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

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

See the full Filesystem policy for all 11 tools.

Get this rule live on your own Filesystem server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY FILESYSTEM →

View all 11 tools →

These attack patterns abuse exactly the kind of access write_file gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so write_file only ever does what you allow.

SECURE FILESYSTEM →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the write_file tool do? +

Create a new file or completely overwrite an existing file with new content. Use with caution as it will overwrite existing files without warning. Handles text content with proper encoding. Only works within allowed directories.. 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_file? +

Register the Filesystem MCP server in PolicyLayer and add a rule for write_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 Filesystem. Nothing to install.

What risk level is write_file? +

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

Can I rate-limit write_file? +

Yes. Add a rate_limit block to the write_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.

How do I block write_file completely? +

Set action: deny in the PolicyLayer policy for write_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.

What MCP server provides write_file? +

write_file is provided by the Filesystem MCP server (@agent-infra/mcp-server-filesystem). 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.

Deterministic rules across all 11 Filesystem tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.