create_embedding · Litellm MCP: Risk & Policy

WHAT IT DOES

What create_embedding does on Litellm

AI agents invoke create_embedding to trigger actions in Litellm. 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 create_embedding needs a policy

This tool executes an external operation (calling LiteLLM/underlying LLM provider APIs) to generate vector embeddings. It is not a simple read of stored data, nor does it write persistent data or cause destruction. It falls under Execute because it triggers external computation/API operations whose cost and effects depend on the input arguments (e.g., model chosen, input size).

From the tool's definition "Generate embeddings using LiteLLM" — triggers an external API call to a language model provider to compute embeddings

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_embedding Rate-limited

create_embedding 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": {
    "create_embedding": {
      "limits": [
        {
          "counter": "create_embedding_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 Litellm, so you can run agents against it safely.

FAQ

Questions about create_embedding

What does the create_embedding tool do? +

Generate embeddings using LiteLLM. It is categorised as a Execute tool in the Litellm MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on create_embedding? +

Register the Litellm MCP server in PolicyLayer and add a rule for create_embedding: 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 Litellm. Nothing to install.

What risk level is create_embedding? +

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

Can I rate-limit create_embedding? +

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

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

create_embedding is provided by the Litellm MCP server (litellm-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.