AI agents call seq_starter_events_stream to retrieve information from Seq without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries log events from a Seq instance with optional filtering. It has no side effects—it merely observes and returns event data from a bounded stream. No creation, modification, deletion, code execution, or financial operations are involved. The bounded stream constraint further limits potential blast radius.
From the tool's definition Tool name includes 'stream' and 'events', description states 'Poll the bounded Seq events stream endpoint for recent/new events'. The verb 'poll' and 'retrieve' indicate data retrieval without modification.
Attacks that exploit this kind of access
Poll the bounded Seq events stream endpoint for recent/new events with optional filter and signal scope. It is categorised as a Read tool in the Seq MCP Server, which means it retrieves data without modifying state.
Register the Seq MCP server in PolicyLayer and add a rule for seq_starter_events_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 Seq. Nothing to install.
seq_starter_events_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 seq_starter_events_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 seq_starter_events_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.
seq_starter_events_stream is provided by the Seq MCP server (mclifeleader/seq-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 →