AI agents invoke create_job to trigger actions in Pgmcp. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The name 'create_job' suggests triggering or scheduling an operation (e.g., a background job for crawling, embedding, or DB administration), which falls under Execute. Given sibling tools like 'embed_corpus', 'get_job', 'get_job_logs', it likely schedules a task that executes external or DB operations. Severity is high due to potential blast radius of arbitrary job execution.
From the tool's definition Tool name 'create_job' on a server that performs PostgreSQL administration, web crawling, and knowledge base management. Description is empty.
Attacks that exploit this kind of access
create_job. It is categorised as a Execute tool in the Pgmcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pg MCP server in PolicyLayer and add a rule for create_job: 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.
create_job is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the create_job 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 create_job. 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.
create_job 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 →