llm_set_model
Set the preferred LLM model for an agent. Search by name or keyword (e.g., 'opus', 'claude-sonnet', 'gpt-4o', 'deepseek', 'llama'). Any model available on OpenRouter can be used.
This record as markdown: /tools/ai-rokha-rokha/llm-set-model.md
What llm_set_model does on Rokha
AI agents use llm_set_model to create or update resources in Rokha, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rokha environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
query | string | Yes | Model name or keyword to search for |
agent_name | string | Yes | Name of the agent to set model for (e.g., 'clawros', 'rokha-agent', 'moros') |
Parameters from the server's own tool schema.
Why llm_set_model is rated Medium
Modifies agent configuration settings reversibly, changing which LLM processes requests.
From the tool's definition Set the preferred LLM model for an agent. Modifies agent configuration.
Attacks that exploit this kind of access
The rule that runs llm_set_model safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Rokha, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For llm_set_model, this is the rule to start with:
llm_set_model 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Rokha, apply this rule, and every llm_set_model call is checked against it from then on.
Questions about llm_set_model
Set the preferred LLM model for an agent. Search by name or keyword (e.g., 'opus', 'claude-sonnet', 'gpt-4o', 'deepseek', 'llama'). Any model available on OpenRouter can be used. It is categorised as a Write tool in the Rokha MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
llm_set_model accepts 2 parameters: query, agent_name. Required: query, agent_name. The full parameter table on this page comes from the server's own tool schema.
Register the Rokha MCP server in PolicyLayer and add a rule for llm_set_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 Rokha. Nothing to install.
llm_set_model is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the llm_set_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 llm_set_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.
llm_set_model is provided by the Rokha MCP server (https://rokha.ai/mcp/jsonrpc). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Rokha, and thousands of servers like it.
This server
Across the catalogue