# team_manager_start_room

Start the approved Team Manager room, dispatch the specialist pool, and persist room state to MongoDB Atlas. Sources can be registered before or after start.

Agent View of the PolicyLayer registry record for `team_manager_start_room`. HTML page: https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-start-room

## Facts

- Tool: `team_manager_start_room`
- Server: Team Manager MCP (`0xadvait/team-manager-mcp`) — https://policylayer.com/tools/0xadvait-team-manager-mcp.md
- Homepage: https://github.com/0xadvait/team-manager-mcp
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "team_manager_start_room",
    "arguments": {}
  }
}
```

## Why team_manager_start_room is rated High

This tool executes a complex operational workflow—dispatching a team of specialist agents and persisting state to a production database. While it doesn't delete data (not Destructive) or move money (not Financial), it actively triggers agent execution and modifies shared MongoDB state that affects downstream team operations.

From the tool's own definition: "Tool 'start_room' performs operational actions: 'dispatch the specialist pool' and 'persist room state to MongoDB Atlas'. These are active operations that trigger execution of external systems (agent dispatch) and data operations on a production database."

## Use case

AI agents invoke team_manager_start_room to trigger actions in Team Manager MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Team Manager MCP:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "team_manager_start_room": {
      "limits": [
        {
          "counter": "team_manager_start_room_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Team Manager MCP (18)

- `team_manager_reset` — Destructive — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-reset.md
- `team_manager_approve_plan` — Execute — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-approve-plan.md
- `team_manager_find_sources` — Read — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-find-sources.md
- `team_manager_ingest_sources` — Read — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-ingest-sources.md
- `team_manager_onboard` — Read — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-onboard.md
- `team_manager_query_context` — Read — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-query-context.md
- `team_manager_state` — Read — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-state.md
- `team_manager_emit_decision` — Write — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-emit-decision.md
- `team_manager_emit_result` — Write — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-emit-result.md
- `team_manager_kill_agent` — Write — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-kill-agent.md
- `team_manager_plan_room` — Write — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-plan-room.md
- `team_manager_post_blackboard` — Write — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-post-blackboard.md
- `team_manager_record_checkpoint` — Write — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-record-checkpoint.md
- `team_manager_register_agents` — Write — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-register-agents.md
- `team_manager_resume_agent` — Write — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-resume-agent.md
- `team_manager_set_sources` — Write — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-set-sources.md
- `team_manager_update_budget` — Write — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-update-budget.md
- `team_manager_write_memory` — Write — https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-write-memory.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=0xadvait-team-manager-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/0xadvait-team-manager-mcp