Capture screen content from a tmux target
AI agents call capture_screen to retrieve information from Agent Collaboration MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads/retrieves the current screen output from a tmux session without modifying state. However, it could expose sensitive information displayed in terminal sessions (credentials, keys, private data), raising the severity to medium despite being a read-only operation.
From the tool's definition Capture screen content from a tmux target
Documented attack patterns abuse exactly the kind of access capture_screen gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Agent Collaboration MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for capture_screen:
{
"version": "1",
"default": "deny",
"tools": {
"capture_screen": {}
}
}capture_screen is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Capture screen content from a tmux target. It is categorised as a Read tool in the Agent Collaboration MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Agent Collaboration MCP Server MCP server in PolicyLayer and add a rule for capture_screen: 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 Agent Collaboration MCP Server. Nothing to install.
capture_screen 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 capture_screen 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 capture_screen. 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.
capture_screen is provided by the Agent Collaboration MCP Server MCP server (nishimoto265/agent_collaboration_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Agent Collaboration MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Agent Collaboration MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.