ruvllm_hnsw_route
Route a query embedding to nearest patterns in HNSW index. 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.
This record as markdown: /tools/io-github-ruvnet-claude-flow/ruvllm-hnsw-route.md
What ruvllm_hnsw_route does on Claude Flow
AI agents call ruvllm_hnsw_route to retrieve information from Claude Flow without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why ruvllm_hnsw_route is rated Low
This tool performs a nearest-neighbor lookup in an HNSW (Hierarchical Navigable Small World) index — a read/query operation that retrieves the closest matching patterns for a given embedding. It does not modify data, execute code, delete anything, or involve financial transactions. It is essentially a semantic search/routing read operation against a local vector index.
From the tool's definition Route a query embedding to nearest patterns in HNSW index
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs ruvllm_hnsw_route 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_hnsw_route, this is the rule to start with:
ruvllm_hnsw_route 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 Claude Flow, apply this rule, and every ruvllm_hnsw_route call is checked against it from then on.
Questions about ruvllm_hnsw_route
Route a query embedding to nearest patterns in HNSW index. 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 Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for ruvllm_hnsw_route: 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_route 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 ruvllm_hnsw_route 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_route. 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_route 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