team_manager_state
Read the current governed room state, including selected agents, source evidence, budget, checkpoints, and decision.
This record as markdown: /tools/0xadvait-team-manager-mcp/team-manager-state.md
What team_manager_state does on Team Manager MCP
AI agents call team_manager_state to retrieve information from Team Manager MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why team_manager_state is rated Low
This is a retrieval-only operation. It queries and returns data about the current state of a governed room without creating, modifying, deleting, or executing any actions. The 'Read' category is appropriate, and severity is low because viewing state information poses minimal risk even if misused by an AI agent.
From the tool's definition Tool description explicitly states 'Read the current governed room state' — a query operation with no side effects. The tool retrieves state information (agents, evidence, budget, checkpoints, decision) without modifying or executing anything.
Attacks that exploit this kind of access
The rule that runs team_manager_state safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Team Manager MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For team_manager_state, this is the rule to start with:
team_manager_state is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Team Manager MCP, apply this rule, and every team_manager_state call is checked against it from then on.
Questions about team_manager_state
Read the current governed room state, including selected agents, source evidence, budget, checkpoints, and decision. It is categorised as a Read tool in the Team Manager MCP MCP Server, which means it retrieves data without modifying state.
Register the Team Manager MCP server in PolicyLayer and add a rule for team_manager_state: 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 Team Manager MCP. Nothing to install.
team_manager_state 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 team_manager_state 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 team_manager_state. 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.
team_manager_state is provided by the Team Manager MCP server (0xadvait/team-manager-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Team Manager, and thousands of servers like it.
This server
Across the catalogue