AI agents call jobs_logs to retrieve information from Run402 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical log entries from job runners. It performs a query operation with optional filtering but does not create, modify, delete, or execute any code. The absence of write, execute, or destructive capabilities, combined with the explicit 'Read' verb in the description, places this firmly in the Read category.
From the tool's definition Tool name 'jobs_logs' and description 'Read recent runner logs for a managed job' explicitly indicate retrieval of log data with no modification capability.
Attacks that exploit this kind of access
Read recent runner logs for a managed job. Use tail to cap entries and since for an ISO-8601 lower bound; legacy epoch milliseconds are still accepted. It is categorised as a Read tool in the Run402 MCP Server, which means it retrieves data without modifying state.
Register the Run402 MCP server in PolicyLayer and add a rule for jobs_logs: 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 Run402. Nothing to install.
jobs_logs 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 jobs_logs 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 jobs_logs. 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.
jobs_logs is provided by the Run402 MCP server (kychee-com/run402). 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 →