Search via RaBitQ quantized index (fast Hamming scan). Returns candidate IDs for reranking. Use when text similarity matters beyond keyword match — native Grep finds exact strings, embeddings find meaning. Pair with memory_store / agentdb_pattern-search to land the vector against your knowledge b...
AI agents call embeddings_rabitq_search to retrieve information from Ruflo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries an embedding index to find similar candidates based on vector similarity. It retrieves information (candidate IDs) without creating, modifying, deleting, or executing arbitrary operations. The blast radius of misuse is minimal — worst case returns irrelevant search results that fail silently. No side effects, no data mutation, no command execution.
From the tool's definition Tool performs 'Search via RaBitQ quantized index' and 'Returns candidate IDs for reranking' — retrieval operations with no modification or deletion of data.
Attacks that exploit this kind of access
Search via RaBitQ quantized index (fast Hamming scan). Returns candidate IDs for reranking. Use when text similarity matters beyond keyword match — native Grep finds exact strings, embeddings find meaning. Pair with memory_store / agentdb_pattern-search to land the vector against your knowledge base. For literal symbol search, native Grep is faster. It is categorised as a Read tool in the Ruflo MCP Server, which means it retrieves data without modifying state.
Register the Ruflo MCP server in PolicyLayer and add a rule for embeddings_rabitq_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 Ruflo. Nothing to install.
embeddings_rabitq_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 embeddings_rabitq_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 embeddings_rabitq_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.
embeddings_rabitq_search is provided by the Ruflo MCP server (ruvnet/ruflo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
embeddings_rabitq_search is one line of Ruflo's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →