cancel_batch_job
AI agents call cancel_batch_job to permanently remove resources in MCP Mistral OCR Optimized — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling a batch job is generally irreversible — once cancelled, the job's progress and queued work are lost and cannot be recovered. This places it in the Destructive category. Confidence is moderate because the description is empty and we are inferring behavior solely from the tool name and sibling context (batch OCR processing server).
From the tool's definition Tool name 'cancel_batch_job' implies irreversible termination of a batch job; description is empty providing no additional context.
Attacks that exploit this kind of access
cancel_batch_job. It is categorised as a Destructive tool in the MCP Mistral OCR Optimized MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Mistral OCR Optimized MCP server in PolicyLayer and add a rule for cancel_batch_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 MCP Mistral OCR Optimized. Nothing to install.
cancel_batch_job is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the cancel_batch_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 cancel_batch_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.
cancel_batch_job is provided by the MCP Mistral OCR Optimized MCP server (snussik/mcp_mistral_ocr_opt). 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 →