recommend_model
Get personalized model recommendations based on use case, budget, and requirements.
This record as markdown: /tools/io-github-daichi-kudo-llm-advisor/recommend-model.md
What recommend_model does on Llm Advisor
AI agents call recommend_model to retrieve information from Llm Advisor without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why recommend_model is rated Low
This tool queries an internal database of 336+ models to return recommendations. It has no side effects—it does not create, modify, delete, or execute anything. The worst-case scenario of misuse (e.g., an AI agent requesting a recommendation) results only in receiving advisory information, not operational changes or resource commitments.
From the tool's definition The tool 'recommend_model' with description 'Get personalized model recommendations based on use case, budget, and requirements' is purely informational.
Attacks that exploit this kind of access
The rule that runs recommend_model safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Llm Advisor, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For recommend_model, this is the rule to start with:
recommend_model is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Llm Advisor, apply this rule, and every recommend_model call is checked against it from then on.
Questions about recommend_model
Get personalized model recommendations based on use case, budget, and requirements. It is categorised as a Read tool in the Llm Advisor MCP Server, which means it retrieves data without modifying state.
Register the Llm Advisor MCP server in PolicyLayer and add a rule for recommend_model: 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 Llm Advisor. Nothing to install.
recommend_model 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 recommend_model 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 recommend_model. 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.
recommend_model is provided by the Llm Advisor MCP server (llm-advisor-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Llm Advisor, and thousands of servers like it.
This server
Across the catalogue