AI agents call get_job_logs to retrieve information from Pgmcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix is a standard naming convention for read-only retrieval operations. While the empty description reduces confidence slightly, contextualizing this tool among sibling operations shows it performs querying rather than side-effects. Retrieving logs has no direct destructive impact and is consistent with Read category semantics (query, fetch, list).
From the tool's definition Tool name 'get_job_logs' indicates retrieval of job log data. Description is empty, but the naming pattern and sibling tools like 'create_job' and 'get_job' suggest this is a query/retrieval operation for existing job logs rather than a creation,…
Attacks that exploit this kind of access
get_job_logs. It is categorised as a Read tool in the Pgmcp MCP Server, which means it retrieves data without modifying state.
Register the Pg MCP server in PolicyLayer and add a rule for get_job_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 Pgmcp. Nothing to install.
get_job_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_job_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_job_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_job_logs is provided by the Pg MCP server (veloper/pgmcp). 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 →