poll_job
Read only an existing image, animation, batch, tool job or workflow run. At most 20 GETs, no create/resubmit. Completed/failed terminal states stop; missing/unrecognised state stops as unknown.
This record as markdown: /tools/thenavidm-bannerbear-mcp-cli/poll-job.md
What poll_job does on Bannerbear Mcp Cli
AI agents call poll_job to retrieve information from Bannerbear Mcp Cli without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
uid | string | Yes | |
account | string | — | |
resource | string | Yes | |
max_polls | integer | — | |
interval_ms | integer | — |
Parameters from the server's own tool schema.
Why poll_job is rated Low
Even though poll_job only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs poll_job safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Bannerbear Mcp Cli, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For poll_job, this is the rule to start with:
poll_job is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Bannerbear Mcp Cli, apply this rule, and every poll_job call is checked against it from then on.
Questions about poll_job
Read only an existing image, animation, batch, tool job or workflow run. At most 20 GETs, no create/resubmit. Completed/failed terminal states stop; missing/unrecognised state stops as unknown. It is categorised as a Read tool in the Bannerbear Mcp Cli MCP Server, which means it retrieves data without modifying state.
poll_job accepts 5 parameters: uid, account, resource, max_polls, interval_ms. Required: uid, resource. The full parameter table on this page comes from the server's own tool schema.
Register the Bannerbear Mcp Cli MCP server in PolicyLayer and add a rule for poll_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 Bannerbear Mcp Cli. Nothing to install.
poll_job 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 poll_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 poll_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.
poll_job is provided by the Bannerbear Mcp Cli MCP server (@thenavidm/bannerbear-mcp-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Bannerbear Mcp Cli, and thousands of servers like it.
This server
Across the catalogue