AI agents call read_stream to retrieve information from KurrentDB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and server context clearly indicate this retrieves event data from a stream. With no description to suggest otherwise, and given the 'read' verb in the name, this is categorized as Read. Severity is low because reading data has minimal blast radius unless the stream contains extremely sensitive information, but by default read operations pose limited risk.
From the tool's definition Tool name 'read_stream' and server description explicitly lists 'tools to read and write events, list streams' — this tool reads events from a stream, which is a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access read_stream gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and KurrentDB MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for read_stream:
{
"version": "1",
"default": "deny",
"tools": {
"read_stream": {}
}
}read_stream 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_stream. It is categorised as a Read tool in the KurrentDB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the KurrentDB MCP Server MCP server in PolicyLayer and add a rule for read_stream: 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 KurrentDB MCP Server. Nothing to install.
read_stream 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_stream 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_stream. 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_stream is provided by the KurrentDB MCP Server MCP server (kurrent-io/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from KurrentDB MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 KurrentDB MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.