AI agents call hash_getall to retrieve information from Redis MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves all fields from a Redis hash. It performs no modification, deletion, or execution of commands with side effects. It is a pure read operation analogous to HGETALL in Redis.
From the tool's definition Tool name 'hash_getall' and description '获取所有哈希字段' (meaning 'get all hash fields') indicate a read-only retrieval operation.
Attacks that exploit this kind of access
获取所有哈希字段. It is categorised as a Read tool in the Redis MCP MCP Server, which means it retrieves data without modifying state.
Register the Redis MCP server in PolicyLayer and add a rule for hash_getall: 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. Nothing to install.
hash_getall 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 hash_getall 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 hash_getall. 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.
hash_getall is provided by the Redis MCP server (pickstar-2002/redis-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
hash_getall is one line of Redis'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 →