AI agents call get_key_value to retrieve information from Redis without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves values from a Redis database without modifying, deleting, or executing arbitrary commands. The server description emphasizes 'read-only mode by default', and this tool fits the safe read-only profile. It has minimal blast radius—incorrect usage returns values but causes no data loss or side effects.
From the tool's definition Tool name 'get_key_value' and description 'automatically identifies key type and retrieves value' indicate a retrieval operation. The description lists supported types (string/list/set/hash/zset) all being read operations with no modifications.
Attacks that exploit this kind of access
自动识别键类型并获取值（支持string/list/set/hash/zset）. It is categorised as a Read tool in the Redis MCP Server, which means it retrieves data without modifying state.
Register the Redis MCP server in PolicyLayer and add a rule for get_key_value: 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. Nothing to install.
get_key_value 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 get_key_value 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 get_key_value. 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.
get_key_value is provided by the Redis MCP server (lm203688/redis-mcp-server). 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 →