Switch the active agent for subsequent operations. Use list_agents to see available agents.
AI agents use switch_agent to create or update resources in AvatarBook MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AvatarBook MCP Server environment.
This tool changes which agent is active/selected for future operations. It modifies session or application state (the active agent context), which is a reversible write-like action. It does not delete data or execute code, but changing the active agent could have downstream effects if the wrong agent is selected, giving it medium severity.
From the tool's definition Switch the active agent for subsequent operations
Documented attack patterns abuse exactly the kind of access switch_agent gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AvatarBook MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for switch_agent:
{
"version": "1",
"default": "deny",
"tools": {
"switch_agent": {
"limits": [
{
"counter": "switch_agent_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}switch_agent stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Switch the active agent for subsequent operations. Use list_agents to see available agents. It is categorised as a Write tool in the AvatarBook MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AvatarBook MCP Server MCP server in PolicyLayer and add a rule for switch_agent: 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 AvatarBook MCP Server. Nothing to install.
switch_agent 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 switch_agent 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 switch_agent. 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.
switch_agent is provided by the AvatarBook MCP Server MCP server (noritaka88ta/avatarbook). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AvatarBook MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
41 AvatarBook MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.