Search for similar vectors using HNSW or IVF indexing. Supports cosine, euclidean, and dot product distance metrics.
AI agents call ruvector_search to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a query/retrieval operation on a vector database. It retrieves or ranks data based on similarity metrics without side effects, reversible changes, code execution, or data destruction. The tool is purely informational and read-only in nature.
From the tool's definition Tool performs 'search for similar vectors' using standard indexing algorithms (HNSW, IVF) and distance metrics (cosine, euclidean, dot product). No modification, deletion, execution, or financial operations are described.
Attacks that exploit this kind of access
Search for similar vectors using HNSW or IVF indexing. Supports cosine, euclidean, and dot product distance metrics. 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 ruvector_search: 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.
ruvector_search 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 ruvector_search 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 ruvector_search. 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.
ruvector_search 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.