content_replace · MCP Claude Code MCP: Risk & Policy

WHAT IT DOES

What content_replace does on MCP Claude Code

AI agents use content_replace 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 content_replace needs a policy

The tool performs file content replacement, which is a Write operation (creates or modifies data reversibly). While the description is missing, the tool name and server's explicit mention of 'modify files' and 'direct file system interactions' strongly indicate this replaces file contents.

From the tool's definition Tool name 'content_replace' with context of 'modify files' and 'direct file system interactions' indicates file modification capability. Description is empty but the name and server context clearly suggest reversible content modification.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

content_replace Rate-limited

content_replace 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": {
    "content_replace": {
      "limits": [
        {
          "counter": "content_replace_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 content_replace

What does the content_replace tool do? +

content_replace. 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 content_replace? +

Register the MCP Claude Code MCP server in PolicyLayer and add a rule for content_replace: 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 content_replace? +

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

Can I rate-limit content_replace? +

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

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

content_replace 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.