AI agents use contact_create to create or update resources in M365 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your M365 environment.
Creating contacts is a Write operation that modifies data reversibly—contacts can be updated or deleted later. It has no permanent destructive effects and doesn't execute arbitrary code or move money. Severity is medium because contact creation at scale could clutter the address book or be used for spam/phishing preparation, but the blast radius is limited to the contacts directory.
From the tool's definition Tool name 'contact_create' indicates creation of contact records in Microsoft 365 Contacts service. Description is empty but the naming pattern and server context (M365 contact management) make the intent clear.
Attacks that exploit this kind of access
contact_create. It is categorised as a Write tool in the M365 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the M365 MCP server in PolicyLayer and add a rule for contact_create: 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 M365. Nothing to install.
contact_create 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 contact_create 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 contact_create. 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.
contact_create is provided by the M365 MCP server (robin-collins/m365-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 →