AI agents call model_recommend to retrieve information from Ensemble without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only analysis of agent and task attributes to recommend a model tier choice. It retrieves or computes information and returns recommendations without side effects, data modification, code execution, or external API calls. The local intelligence infrastructure context confirms no external calls are made.
From the tool's definition Tool name 'model_recommend' and description 'Recommend a model tier (best/mid/cheapest) for an agent and task' indicate a retrieval/recommendation function that queries model metadata and returns suggestions without modifying state or triggering external…
Attacks that exploit this kind of access
Recommend a model tier (best/mid/cheapest) for an agent and task. It is categorised as a Read tool in the Ensemble MCP Server, which means it retrieves data without modifying state.
Register the Ensemble MCP server in PolicyLayer and add a rule for model_recommend: 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 Ensemble. Nothing to install.
model_recommend is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the model_recommend 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.
Set action: deny in the PolicyLayer policy for model_recommend. 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.
model_recommend is provided by the Ensemble MCP server (lynkbyte/ensemble). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →