AI agents call ms_server_info to retrieve information from M365 MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely retrieves and queries internal server metadata without side effects, making it a Read operation. The severity is low because exposure of server metadata poses minimal risk—it does not access user data, execute operations, or cause irreversible changes. The confidence is high due to the clear, self-explanatory description.
From the tool's definition Tool returns server metadata (version, available tools, runtime info) with no modification or execution capability. Description explicitly states it is for debugging and information retrieval only.
Attacks that exploit this kind of access
Returns m365-mcp server metadata: version, available tools, and runtime info. Useful for debugging. It is categorised as a Read tool in the M365 MCP MCP Server, which means it retrieves data without modifying state.
Register the M365 MCP server in PolicyLayer and add a rule for ms_server_info: 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 MCP. Nothing to install.
ms_server_info 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 ms_server_info 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 ms_server_info. 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.
ms_server_info is provided by the M365 MCP server (stumason/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 →