send_multimodal · OpenClaude MCP Server MCP: Risk & Policy

WHAT IT DOES

What send_multimodal does on OpenClaude MCP Server

AI agents invoke send_multimodal to trigger actions in OpenClaude MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why send_multimodal needs a policy

Sending a prompt to a running LLM session initiates external computation and can trigger downstream actions depending on what tools or capabilities the session has access to. This goes beyond a simple read or write operation; it executes inference against a live session. The multimodal aspect (image attachments) expands the attack surface but doesn't change the core category.

From the tool's definition 'Send a prompt with image attachments to a running OpenClaude session' — triggers execution of a prompt (with multimodal input) against an active LLM session, causing external computation and potentially side effects depending on session tools/context.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_multimodal Rate-limited

send_multimodal stays usable, but rate-capped — a runaway agent can't fire it dozens of times 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_multimodal": {
      "limits": [
        {
          "counter": "send_multimodal_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about send_multimodal

What does the send_multimodal tool do? +

Send a prompt with image attachments to a running OpenClaude session. It is categorised as a Execute tool in the OpenClaude MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on send_multimodal? +

Register the OpenClaude MCP Server MCP server in PolicyLayer and add a rule for send_multimodal: 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 OpenClaude MCP Server. Nothing to install.

What risk level is send_multimodal? +

send_multimodal is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit send_multimodal? +

Yes. Add a rate_limit block to the send_multimodal 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_multimodal completely? +

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

send_multimodal is provided by the OpenClaude MCP Server MCP server (sandraschi/openclaude-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.