Format chat messages using a template (llama3, mistral, chatml, phi, gemma, or auto-detect). 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 Claud...
AI agents invoke ruvllm_chat_format to trigger actions in Claude Flow. 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.
This tool formats prompts and triggers local inference execution (not just data transformation), routing prompts to local LLM backends. It executes inference operations whose effects depend on the template and prompt arguments. While it could be argued as a Write or Read operation, the invocation of local inference pipelines (MicroLoRA adapters, local model execution) makes Execute the most accurate category.
From the tool's definition Format chat messages using a template (llama3, mistral, chatml, phi, gemma, or auto-detect)... you need local inference — air-gapped environments, MicroLoRA-fine-tuned per-task adapters
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Format chat messages using a template (llama3, mistral, chatml, phi, gemma, or auto-detect). 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 Execute tool in the Claude Flow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Flow MCP server in PolicyLayer and add a rule for ruvllm_chat_format: 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_chat_format is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ruvllm_chat_format 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_chat_format. 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_chat_format 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.