Encerra gravação, faz pull do MP4 e retorna artifact local.
AI agents call screenrecord_stop to retrieve information from AVD MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool stops a screen recording and pulls the MP4 file to local storage, returning it as an artifact. The primary action is retrieving/transferring a file (pull + return artifact), which is Read. However, it also stops an ongoing process (side effect), and the description is partially uninformative (Portuguese, brief).
From the tool's definition Encerra gravação, faz pull do MP4 e retorna artifact local
Attacks that exploit this kind of access
Encerra gravação, faz pull do MP4 e retorna artifact local. It is categorised as a Read tool in the AVD MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AVD MCP Server MCP server in PolicyLayer and add a rule for screenrecord_stop: 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 AVD MCP Server. Nothing to install.
screenrecord_stop 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 screenrecord_stop 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 screenrecord_stop. 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.
screenrecord_stop is provided by the AVD MCP Server MCP server (jramalho/avd-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 →