Add an entry to a Redis Stream. Streams are append-only logs ideal for
AI agents use redis_stream_add to create or update resources in RedisNexus — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your RedisNexus environment.
This tool creates or modifies data by appending entries to a Redis Stream. It is reversible (entries can be deleted), so it does not qualify as Destructive. It does not execute arbitrary code, delete data, or move money. Write is the appropriate category.
From the tool's definition Tool name 'redis_stream_add' and description 'Add an entry to a Redis Stream' indicate data creation/modification. Streams are append-only logs, making this a write operation that creates new entries reversibly.
Attacks that exploit this kind of access
Add an entry to a Redis Stream. Streams are append-only logs ideal for. It is categorised as a Write tool in the RedisNexus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the RedisNexus MCP server in PolicyLayer and add a rule for redis_stream_add: 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_add is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the redis_stream_add 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_add. 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_add 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 →