Publish or unpublish an agent. Published agents are live and handle incoming conversations. Unpublished agents are in
AI agents use publish_agent to create or update resources in BotUyo MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your BotUyo MCP Server environment.
Publishing or unpublishing an agent changes its live status, making it active and able to handle real conversations or taking it offline. This is a reversible state change (can publish/unpublish), so it falls under Write rather than Destructive.
From the tool's definition 'Publish or unpublish an agent. Published agents are live and handle incoming conversations.'
Attacks that exploit this kind of access
Publish or unpublish an agent. Published agents are live and handle incoming conversations. Unpublished agents are in. It is categorised as a Write tool in the BotUyo MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the BotUyo MCP Server MCP server in PolicyLayer and add a rule for publish_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 BotUyo MCP Server. Nothing to install.
publish_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 publish_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 publish_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.
publish_agent is provided by the BotUyo MCP Server MCP server (marcoar1/botuyo-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 →