获取所有设备及其输出值
AI agents call vicon_get_devices to retrieve information from Vicon DataStream MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves device information from the Vicon motion capture system. It performs a read-only query operation with no side effects—no data is created, modified, deleted, or executed. The blast radius of misuse is minimal, as an agent gaining access to this tool could only view device inventory and status information, not affect hardware state or data integrity.
From the tool's definition Tool name 'vicon_get_devices' and description '获取所有设备及其输出值' (get all devices and their output values) indicate a retrieval operation. The tool queries device information without modifying, executing, or deleting data.
Attacks that exploit this kind of access
获取所有设备及其输出值. It is categorised as a Read tool in the Vicon DataStream MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Vicon DataStream MCP Server MCP server in PolicyLayer and add a rule for vicon_get_devices: 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 Vicon DataStream MCP Server. Nothing to install.
vicon_get_devices 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 vicon_get_devices 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 vicon_get_devices. 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.
vicon_get_devices is provided by the Vicon DataStream MCP Server MCP server (ros-claw/vicon-datastream-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 →