roboflow_download_export
AI agents call roboflow_download_export to retrieve information from Roboflow MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although the tool description is empty (reducing confidence slightly), the name 'roboflow_download_export' strongly suggests retrieving/exporting data from a project or dataset without modification. Severity is medium rather than low because exporting a dataset could expose sensitive training data or proprietary ML models if an agent mishandles access controls or exports the wrong project.
From the tool's definition Tool name contains 'download_export' and is part of a dataset/project management API that includes read operations like roboflow_get_image, roboflow_get_project, and roboflow_get_version.
Attacks that exploit this kind of access
roboflow_download_export. It is categorised as a Read tool in the Roboflow MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Roboflow MCP Server MCP server in PolicyLayer and add a rule for roboflow_download_export: 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 Roboflow MCP Server. Nothing to install.
roboflow_download_export 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 roboflow_download_export 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 roboflow_download_export. 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.
roboflow_download_export is provided by the Roboflow MCP Server MCP server (mayankd409/roboflow-mcp-server). 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 →