Detect objects in an image or video. Accepts a URL or local file path.
AI agents call detect to retrieve information from Perceptron Vision MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Object detection is a read-only analysis operation that retrieves information about visual content. The tool processes images/videos to extract object locations and classifications but does not create, modify, delete, execute code, move money, or perform irreversible actions.
From the tool's definition Tool accepts 'a URL or local file path' and 'detects objects in an image or video' — a query operation that analyzes visual content without modifying, executing external operations, or triggering side effects.
Attacks that exploit this kind of access
Detect objects in an image or video. Accepts a URL or local file path. It is categorised as a Read tool in the Perceptron Vision MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Perceptron Vision MCP Server MCP server in PolicyLayer and add a rule for detect: 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 Perceptron Vision MCP Server. Nothing to install.
detect 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 detect 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 detect. 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.
detect is provided by the Perceptron Vision MCP Server MCP server (perceptron-ai-inc/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 →