Capture the user
AI agents call screenshot to retrieve information from MTM - MCP Telegram MORE without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screenshots are retrieval operations that capture visual information without side effects or data modification. However, in the context of a Telegram bot controlling Claude sessions, screenshot capability poses a medium severity risk because it could capture sensitive information visible on screen (credentials, private messages, personal data).
From the tool's definition Tool name is 'screenshot' and description states 'Capture the user' - this captures visual/screen data without modifying it.
Attacks that exploit this kind of access
Capture the user. It is categorised as a Read tool in the MTM - MCP Telegram MORE MCP Server, which means it retrieves data without modifying state.
Register the MTM - MCP Telegram MORE MCP server in PolicyLayer and add a rule for screenshot: 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 MTM - MCP Telegram MORE. Nothing to install.
screenshot 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 screenshot 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 screenshot. 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.
screenshot is provided by the MTM - MCP Telegram MORE MCP server (v0idhrt/MTM---MCP-Telegram-MORE). 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 →