AI agents use join_team to create or update resources in ATMcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ATMcp environment.
The tool creates or modifies team membership state by adding an agent to a team using a join token. This is reversible (agents can leave teams), produces persistent side effects in a shared multi-agent system, and affects downstream operations (agent can now access team resources, participate in task distribution).
From the tool's definition Tool name 'join_team' and context of team-based multi-agent system indicates creating or modifying organizational state. Description states 'Join (or re-join) a team' which involves writing membership data to a distributed system.
Attacks that exploit this kind of access
Join (or re-join) a team. The join token may be passed here or sent as an. It is categorised as a Write tool in the ATMcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AT MCP server in PolicyLayer and add a rule for join_team: 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 ATMcp. Nothing to install.
join_team is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the join_team 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 join_team. 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.
join_team is provided by the AT MCP server (midcheck/atmcp). 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 →