Poll an async transcription job created by transcribe-audio.
AI agents call transcribe_get_job to retrieve information from Video Toolkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the state of an asynchronous transcription job that was previously initiated. Polling for job status is a non-destructive read operation with no side effects. It does not create, modify, delete, or execute any operations—it merely retrieves information about an in-progress job. The blast radius of misuse is minimal, as checking job status cannot harm systems or data.
From the tool's definition Tool performs polling/status retrieval on an existing transcription job. The verb 'get' and description 'Poll an async transcription job' indicate a read-only query operation that retrieves job status without modifying data.
Attacks that exploit this kind of access
Poll an async transcription job created by transcribe-audio. It is categorised as a Read tool in the Video Toolkit MCP Server, which means it retrieves data without modifying state.
Register the Video Toolkit MCP server in PolicyLayer and add a rule for transcribe_get_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 Video Toolkit. Nothing to install.
transcribe_get_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 transcribe_get_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 transcribe_get_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.
transcribe_get_job is provided by the Video Toolkit MCP server (jamesanz/transcript-mcp). 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 →