View the task board and who's online (auto-marks stale agents offline).
AI agents call view_board to retrieve information from Claude Team MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about task board status and agent availability without creating, modifying, or deleting any data. The marking of stale agents as offline is a transient status reflection, not a destructive or irreversible action. It is a pure query/retrieval operation with no blast radius.
From the tool's definition Tool name 'view_board' and description 'View the task board and who's online' indicate a read-only operation. The action of 'auto-marks stale agents offline' is a display/status update with no persistent side effects on actual tasks or data.
Attacks that exploit this kind of access
View the task board and who's online (auto-marks stale agents offline). It is categorised as a Read tool in the Claude Team MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Team MCP server in PolicyLayer and add a rule for view_board: 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 Claude Team MCP. Nothing to install.
view_board 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 view_board 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 view_board. 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.
view_board is provided by the Claude Team MCP server (lakshan12367/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 →