ruvllm_generate_config
Create a generation config (maxTokens, temperature, topP, etc.) as JSON. Use when sending every prompt to the Anthropic API is wrong because you need local inference — air-gapped environments, MicroLoRA-fine-tuned per-task adapters, or sub-cent per-call cost. For general Claude work native Task i...
This record as markdown: /tools/io-github-ruvnet-claude-flow/ruvllm-generate-config.md
What ruvllm_generate_config does on Claude Flow
AI agents use ruvllm_generate_config to create or update resources in Claude Flow, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Flow environment.
Why ruvllm_generate_config is rated Medium
This tool creates and modifies configuration data (generation parameters like maxTokens, temperature, topP) that will be persisted and used by downstream inference systems. While it does not delete data or execute arbitrary code, it writes configuration that affects AI model behavior in potentially consequential ways.
From the tool's definition Tool description states 'Create a generation config...as JSON' and explicitly mentions creating configuration objects for local inference systems.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs ruvllm_generate_config safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Flow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ruvllm_generate_config, this is the rule to start with:
ruvllm_generate_config 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 Claude Flow, apply this rule, and every ruvllm_generate_config call is checked against it from then on.
Questions about ruvllm_generate_config
Create a generation config (maxTokens, temperature, topP, etc.) as JSON. Use when sending every prompt to the Anthropic API is wrong because you need local inference — air-gapped environments, MicroLoRA-fine-tuned per-task adapters, or sub-cent per-call cost. For general Claude work native Task is the right call. It is categorised as a Write tool in the Claude Flow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Flow MCP server in PolicyLayer and add a rule for ruvllm_generate_config: 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 Claude Flow. Nothing to install.
ruvllm_generate_config 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 ruvllm_generate_config 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 ruvllm_generate_config. 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.
ruvllm_generate_config is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Claude Flow, and thousands of servers like it.
This server
Across the catalogue