AI agents call get-run-logs to retrieve information from Trigger Dev 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 data from a completed or running task without side effects. It is a read-only operation that queries stored logs. The severity is low because log data is typically informational and non-sensitive in most contexts, though confidence is slightly reduced due to the lack of additional context about what sensitive information might be present in logs.
From the tool's definition Tool name 'get-run-logs' and description 'Retrieve the logs output of a task run' indicate data retrieval with no modification or execution capability.
Documented attack patterns abuse exactly the kind of access get-run-logs gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trigger Dev, and nothing reaches the server without passing your rules. This is the rule we recommend for get-run-logs:
{
"version": "1",
"default": "deny",
"tools": {
"get-run-logs": {}
}
}get-run-logs 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.
Retrieve the logs output of a task run. It is categorised as a Read tool in the Trigger Dev MCP Server, which means it retrieves data without modifying state.
Register the Trigger Dev MCP server in PolicyLayer and add a rule for get-run-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 Trigger Dev. Nothing to install.
get-run-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 get-run-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 get-run-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.
get-run-logs is provided by the Trigger Dev MCP server (@triggerdotdev/trigger.dev). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Trigger Dev tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
6 Trigger Dev tools catalogued and risk-classified — across an index of 42,500+ MCP servers.