AI agents call get_job_log to retrieve information from Gitlab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns existing job log data without modifying, executing, or deleting anything. While CI/CD logs may contain sensitive information (credentials, internal paths), the tool itself performs only a read operation. The severity is low because reading logs has no direct side effects on the system state, though information disclosure risks depend on log contents and access controls.
From the tool's definition Tool description states 'Get the raw log/trace output of a job' — a retrieval operation with no modification, deletion, or execution of code. The verb 'get' and focus on reading output are clear indicators of a Read operation.
Documented attack patterns abuse exactly the kind of access get_job_log gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gitlab, and nothing reaches the server without passing your rules. This is the rule we recommend for get_job_log:
{
"version": "1",
"default": "deny",
"tools": {
"get_job_log": {}
}
}get_job_log 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.
Get the raw log/trace output of a job. It is categorised as a Read tool in the Gitlab MCP Server, which means it retrieves data without modifying state.
Register the Gitlab MCP server in PolicyLayer and add a rule for get_job_log: 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 Gitlab. Nothing to install.
get_job_log 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_job_log 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_job_log. 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_job_log is provided by the Gitlab MCP server (yoda-digital/mcp-gitlab-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 88 Gitlab tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
88 Gitlab tools catalogued and risk-classified — across an index of 42,500+ MCP servers.