Read entries from a Redis Stream within an ID range.
AI agents call redis_stream_read to retrieve information from RedisNexus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from a Redis Stream without side effects. It queries existing entries within a specified ID range but does not create, modify, delete, or execute any operations. The read-only nature and lack of state-changing operations place it firmly in the Read category with low severity risk, as misuse would result only in unauthorized data access rather than destructive or operational harm.
From the tool's definition Tool name is 'redis_stream_read' and description states 'Read entries from a Redis Stream within an ID range' - explicitly a read operation with no modification or deletion.
Attacks that exploit this kind of access
Read entries from a Redis Stream within an ID range. It is categorised as a Read tool in the RedisNexus MCP Server, which means it retrieves data without modifying state.
Register the RedisNexus MCP server in PolicyLayer and add a rule for redis_stream_read: 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 RedisNexus. Nothing to install.
redis_stream_read 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 redis_stream_read 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 redis_stream_read. 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.
redis_stream_read is provided by the RedisNexus MCP server (rajkumar-madhu/mcp). 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 →