send_claude_output · Code Context MCP: Risk & Policy

WHAT IT DOES

What send_claude_output does on Code Context

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

WHY IT NEEDS A POLICY

Why send_claude_output needs a policy

An AI agent can call send_claude_output faster than any human can review — one bad instruction and it creates or modifies resources in Code Context by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_claude_output Rate-limited

send_claude_output 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": {
    "send_claude_output": {
      "limits": [
        {
          "counter": "send_claude_output_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 Code Context, so you can run agents against it safely.

FAQ

Questions about send_claude_output

What does the send_claude_output tool do? +

Stream Claude. It is categorised as a Write tool in the Code Context MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_claude_output? +

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

What risk level is send_claude_output? +

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

Can I rate-limit send_claude_output? +

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

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

send_claude_output is provided by the Code Context MCP server (velimirmueller/vlm-code-context-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.