ruvllm_hnsw_create · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What ruvllm_hnsw_create does on Claude Flow

AI agents use ruvllm_hnsw_create 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 IT NEEDS A POLICY

Why ruvllm_hnsw_create needs a policy

The tool creates a new HNSW (Hierarchical Navigable Small World) router instance compiled to WASM. This is a Write operation as it instantiates a new persistent routing structure. It does not execute arbitrary code or commands, nor does it delete or move money.

From the tool's definition 'Create a WASM HNSW router for semantic pattern routing' — this creates a new routing component/resource in the system

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ruvllm_hnsw_create Rate-limited

ruvllm_hnsw_create 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ruvllm_hnsw_create": {
      "limits": [
        {
          "counter": "ruvllm_hnsw_create_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude Flow, so you can run agents against it safely.

FAQ

Questions about ruvllm_hnsw_create

What does the ruvllm_hnsw_create tool do? +

Create a WASM HNSW router for semantic pattern routing. Max ~11 patterns (v2.0.1 limit). 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.

How do I enforce a policy on ruvllm_hnsw_create? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for ruvllm_hnsw_create: 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.

What risk level is ruvllm_hnsw_create? +

ruvllm_hnsw_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit ruvllm_hnsw_create? +

Yes. Add a rate_limit block to the ruvllm_hnsw_create 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.

How do I block ruvllm_hnsw_create completely? +

Set action: deny in the PolicyLayer policy for ruvllm_hnsw_create. 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.

What MCP server provides ruvllm_hnsw_create? +

ruvllm_hnsw_create 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.