vector_search_hash
AI agents call vector_search_hash to retrieve information from Redis MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Vector search queries data from Redis without modifying it. No side effects, no data creation/deletion, no code execution, and no financial impact. This is a classic Read operation. Low severity because querying data has minimal blast radius even if misused—worst case is information disclosure of existing data.
From the tool's definition Tool name 'vector_search_hash' indicates a search operation over vector data stored in Redis hashes. The server description explicitly lists 'vector search' as a supported capability alongside other data retrieval operations like get, list, and search.
Attacks that exploit this kind of access
vector_search_hash. It is categorised as a Read tool in the Redis MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Redis MCP Server MCP server in PolicyLayer and add a rule for vector_search_hash: 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 Redis MCP Server. Nothing to install.
vector_search_hash 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 vector_search_hash 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 vector_search_hash. 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.
vector_search_hash is provided by the Redis MCP Server MCP server (yuchenhui/mcp-redis). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →