Add a pattern to an HNSW router. Embedding must match router dimensions. 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...
AI agents use ruvllm_hnsw_add 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.
The tool modifies a vector search index (HNSW) by adding patterns, which is a reversible write operation. Severity is medium rather than high because the blast radius is constrained to the local routing layer—it affects inference routing logic rather than core data or financial systems. However, corrupting routing patterns could degrade model selection or cause silent misrouting of prompts, hence not low.
From the tool's definition Add a pattern to an HNSW router. Embedding must match router dimensions.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Add a pattern to an HNSW router. Embedding must match router dimensions. 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_hnsw_add: 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_hnsw_add 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_hnsw_add 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_hnsw_add. 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_hnsw_add 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.