download_batch_results
AI agents call download_batch_results to retrieve information from MCP Mistral OCR Optimized without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool downloads results from completed batch jobs, which is a read operation that retrieves data with no side effects. While the description is empty (reducing confidence slightly), the name and context within a batch OCR processing workflow strongly suggest this retrieves stored outputs rather than executing, modifying, or destroying data.
From the tool's definition Tool name 'download_batch_results' indicates retrieval of previously computed OCR outputs. No description provided, but context shows this is part of a batch processing pipeline (create_batch_job, check_batch_status, process_batch_local_files) where results…
Attacks that exploit this kind of access
download_batch_results. It is categorised as a Read tool in the MCP Mistral OCR Optimized MCP Server, which means it retrieves data without modifying state.
Register the MCP Mistral OCR Optimized MCP server in PolicyLayer and add a rule for download_batch_results: 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.
download_batch_results 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 download_batch_results 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 download_batch_results. 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.
download_batch_results 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 →