AI agents call contact_get to retrieve information from M365 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name strongly suggests a simple retrieval/query operation for contact information with no side effects. While the description is empty (lowering confidence slightly), the naming pattern is clear. Contact retrieval is a read-only operation with minimal blast radius if misused—it retrieves existing data without modification, deletion, or external execution.
From the tool's definition Tool name 'contact_get' indicates retrieval of contact data. The prefix 'contact_' combined with 'get' action follows standard Read operation naming conventions seen alongside other tools like 'calendar_check_availability' on this server.
Attacks that exploit this kind of access
contact_get. It is categorised as a Read tool in the M365 MCP Server, which means it retrieves data without modifying state.
Register the M365 MCP server in PolicyLayer and add a rule for contact_get: 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_get is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the contact_get 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_get. 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_get 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 →