write · MCP Claude Code MCP: Risk & Policy

WHAT IT DOES

What write does on MCP Claude Code

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

WHY IT NEEDS A POLICY

Why write needs a policy

The 'write' tool creates or modifies file contents reversibly. While the description is empty (lowering confidence slightly), the server's stated capability to 'modify files' and 'direct file system interactions' combined with the tool name 'write' strongly indicates this performs Write operations.

From the tool's definition Tool named 'write' on a server that 'modify files' and implements 'direct file system interactions.' The tool description is empty, but context from the server description establishes that this server enables file modification.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

write Rate-limited

write 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": {
    "write": {
      "limits": [
        {
          "counter": "write_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP Claude Code, so you can run agents against it safely.

FAQ

Questions about write

What does the write tool do? +

write. It is categorised as a Write tool in the MCP Claude Code 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? +

Register the MCP Claude Code MCP server in PolicyLayer and add a rule for write: 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 MCP Claude Code. Nothing to install.

What risk level is write? +

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

Can I rate-limit write? +

Yes. Add a rate_limit block to the write 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 completely? +

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

write is provided by the MCP Claude Code MCP server (sdglbl/mcp-claude-code). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.