Auto-assign a task to the best-matching IDLE agent based on declared skills
AI agents use auto_assign to create or update resources in Claude Team MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Team MCP environment.
This tool creates or updates task assignments—a reversible modification of task state and agent workload. While it affects workflow coordination, it does not execute arbitrary code, delete data irreversibly, move money, or perform financial operations.
From the tool's definition Tool performs 'auto-assign' action which creates or modifies task assignments to agents. The description states it assigns 'a task to...agent', indicating it writes/modifies state in the task management system.
Attacks that exploit this kind of access
Auto-assign a task to the best-matching IDLE agent based on declared skills. It is categorised as a Write tool in the Claude Team MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Team MCP server in PolicyLayer and add a rule for auto_assign: 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.
auto_assign 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 auto_assign 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 auto_assign. 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.
auto_assign 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 →