AI agents call server_get_version 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.
This tool queries server version metadata, a read-only operation with no ability to modify, delete, or execute code. The empty description reduces confidence slightly, but the semantic meaning of 'get_version' is unambiguous. Severity is low because even if exposed, reading version information poses minimal risk compared to other tool categories.
From the tool's definition Tool name 'server_get_version' indicates it retrieves version information with no side effects. Description is empty, but the naming pattern is clear: get_ prefix typically retrieves data without modification.
Attacks that exploit this kind of access
server_get_version. 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 server_get_version: 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.
server_get_version 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 server_get_version 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 server_get_version. 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.
server_get_version 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 →