private_streamable_append · Claude Imagine MCP

WHAT IT DOES

What private_streamable_append does on Claude Imagine

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

WHY IT NEEDS A POLICY

Why private_streamable_append needs a policy

This tool appends HTML content to a streaming UI element, which is a reversible write/modification operation. It creates or modifies web interface content without permanently destroying data. The severity is medium because injecting arbitrary HTML could introduce XSS or unintended UI manipulation if misused by an AI agent, but the operation itself is not irreversible.

From the tool's definition Append a chunk of HTML to a streaming element

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

private_streamable_append Rate-limited

private_streamable_append 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": {
    "private_streamable_append": {
      "limits": [
        {
          "counter": "private_streamable_append_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 Claude Imagine, so you can run agents against it safely.

FAQ

Questions about private_streamable_append

What does the private_streamable_append tool do? +

Append a chunk of HTML to a streaming element. It is categorised as a Write tool in the Claude Imagine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on private_streamable_append? +

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

What risk level is private_streamable_append? +

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

Can I rate-limit private_streamable_append? +

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

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

private_streamable_append is provided by the Claude Imagine MCP server (t3rm1nu55/claudeimagine). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.