Medium Risk

write_document

Write content to document files in specified formats. Output directory is controlled by OUTPUT_DIR environment variable. Files will be automatically saved to OUTPUT_DIR with auto-generated names based on content type (HTML, Markdown, or plain text). Supports intelligent format detection.

How to control write_document ↓

AI agents use write_document to create or update resources in Doc Ops — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Doc Ops environment.

Medium Risk

This tool creates or modifies document files, which is a reversible write operation. It does not delete data (would be Destructive), execute arbitrary code (would be Execute), or move money (would be Financial).

From the tool's definition Tool name is 'write_document' and description states 'Write content to document files in specified formats' and 'Files will be automatically saved to OUTPUT_DIR'.

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

PolicyLayer is an MCP gateway — it sits between your AI agents and Doc Ops, and nothing reaches the server without passing your rules. This is the rule we recommend for write_document:

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

write_document 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 Doc Ops — 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.

Go deeper

What does the write_document tool do? +

Write content to document files in specified formats. Output directory is controlled by OUTPUT_DIR environment variable. Files will be automatically saved to OUTPUT_DIR with auto-generated names based on content type (HTML, Markdown, or plain text). Supports intelligent format detection. It is categorised as a Write tool in the Doc Ops 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_document? +

Register the Doc Ops MCP server in PolicyLayer and add a rule for write_document: 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 Doc Ops. Nothing to install.

What risk level is write_document? +

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

Can I rate-limit write_document? +

Yes. Add a rate_limit block to the write_document 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_document completely? +

Set action: deny in the PolicyLayer policy for write_document. 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_document? +

write_document is provided by the Doc Ops MCP server (tele-ai/doc-ops-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Doc Ops tool call.

Deterministic rules across all 13 Doc Ops tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

13 Doc Ops tools catalogued and risk-classified — across an index of 42,500+ 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.