Read pending pub/sub messages for an existing subscription. Args: subscription_id: The ID returned by subscribe() or psubscribe(). timeout_ms: Time to wait for messages in milliseconds. Use 0 for non-blocking. max_messages: Maximum number of messages to return in one call. Returns: A dictionary c...
AI agents call read_messages 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.
This tool performs a passive read operation on Redis pub/sub messages. It retrieves data that is already pending in a subscription with no side effects, matching the 'Read' category definition of querying/retrieving data without side effects. The timeout and max_messages parameters only control retrieval behavior, not data mutation.
From the tool's definition Tool description explicitly states 'Read pending pub/sub messages' and 'Returns: A dictionary containing the collected messages'. The operation retrieves existing messages without modifying, deleting, or executing code.
Documented attack patterns abuse exactly the kind of access read_messages gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Redis MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for read_messages:
{
"version": "1",
"default": "deny",
"tools": {
"read_messages": {}
}
}read_messages is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read pending pub/sub messages for an existing subscription. Args: subscription_id: The ID returned by subscribe() or psubscribe(). timeout_ms: Time to wait for messages in milliseconds. Use 0 for non-blocking. max_messages: Maximum number of messages to return in one call. Returns: A dictionary containing the collected messages or an error message. 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 read_messages: 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.
read_messages 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 read_messages 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 read_messages. 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.
read_messages is provided by the Redis MCP Server MCP server (redis/mcp-redis). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 53 Redis MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
53 Redis MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.