Reassign ownership of an agent to a different user in the organization.
AI agents use reassign_agent to create or update resources in Agent 365 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent 365 environment.
This tool modifies the ownership/assignment of an agent resource, which is a reversible write operation (ownership can be reassigned again). However, the blast radius is high because transferring ownership of an AI agent to the wrong user could result in loss of control, unauthorized access, or misuse of that agent's capabilities within the M365 environment.
From the tool's definition Reassign ownership of an agent to a different user in the organization.
Documented attack patterns abuse exactly the kind of access reassign_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 reassign_agent:
{
"version": "1",
"default": "deny",
"tools": {
"reassign_agent": {
"limits": [
{
"counter": "reassign_agent_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}reassign_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.
Reassign ownership of an agent to a different user in the organization. It is categorised as a Write tool in the Agent 365 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agent 365 MCP server in PolicyLayer and add a rule for reassign_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.
reassign_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 reassign_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 reassign_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.
reassign_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.