Block a specific agent by ID. This prevents the agent from being used by anyone in the organization.
AI agents call block_agent to permanently remove resources in Agent 365 — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Blocking an agent organization-wide is a highly impactful, potentially irreversible action that disables access for all users across the organization. While a sibling 'unblock_agent' tool exists (suggesting some reversibility), the blast radius of disabling an agent for an entire organization is high.
From the tool's definition Block a specific agent by ID. This prevents the agent from being used by anyone in the organization.
Documented attack patterns abuse exactly the kind of access block_agent gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Agent 365, and nothing reaches the server without passing your rules. This is the rule we recommend for block_agent:
{
"version": "1",
"default": "deny",
"hide": [
"block_agent"
]
}block_agent disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Block a specific agent by ID. This prevents the agent from being used by anyone in the organization. It is categorised as a Destructive tool in the Agent 365 MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Agent 365 MCP server in PolicyLayer and add a rule for block_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 Agent 365. Nothing to install.
block_agent is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the block_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 block_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.
block_agent is provided by the Agent 365 MCP server (ramakrishnan24689/agent365-mcpapp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Agent 365, 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.
5 Agent 365 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.