AI agents invoke wait_job_completion to trigger actions in PDF Co MCP Server. 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 tool likely triggers or monitors an external operation (PDF processing job), which is characteristic of Execute. However, confidence is moderate due to missing description and the passive nature of 'wait'—this may be purely a Read operation if it only queries job status without side effects. Without more detail, the Execute classification accounts for potential job triggering/state changes.
From the tool's definition Tool name 'wait_job_completion' suggests polling or blocking for an asynchronous job result. No description provided to clarify exact behavior.
Documented attack patterns abuse exactly the kind of access wait_job_completion gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PDF Co MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for wait_job_completion:
{
"version": "1",
"default": "deny",
"tools": {
"wait_job_completion": {
"limits": [
{
"counter": "wait_job_completion_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}wait_job_completion stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
wait_job_completion. It is categorised as a Execute tool in the PDF Co MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PDF Co MCP Server MCP server in PolicyLayer and add a rule for wait_job_completion: 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 PDF Co MCP Server. Nothing to install.
wait_job_completion 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 wait_job_completion 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 wait_job_completion. 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.
wait_job_completion is provided by the PDF Co MCP Server MCP server (pdfdotco/pdfco-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from PDF Co MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
38 PDF Co MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.