Extract text from PDF files (local or URL) using Mistral OCR. Accepts multiple sources.
AI agents call ocr_pdf to retrieve information from Mistral Ai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
OCR extraction is a read-only operation that retrieves and processes visual content into text format without altering the source document or creating irreversible changes. The operation is non-destructive and produces derived data from inputs without side effects on system state or external services.
From the tool's definition Tool name 'ocr_pdf' and description 'Extract text from PDF files' indicates retrieval of text content with no modification or side effects.
Attacks that exploit this kind of access
Extract text from PDF files (local or URL) using Mistral OCR. Accepts multiple sources. It is categorised as a Read tool in the Mistral Ai MCP Server, which means it retrieves data without modifying state.
Register the Mistral Ai MCP server in PolicyLayer and add a rule for ocr_pdf: 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 Mistral Ai. Nothing to install.
ocr_pdf 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 ocr_pdf 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 ocr_pdf. 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.
ocr_pdf is provided by the Mistral Ai MCP server (tan-yong-sheng/mistral-ai-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 →