AI agents call ms_transcripts 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 retrieves stored meeting transcripts without modifying, executing, or deleting data. However, meeting transcripts may contain sensitive business information, customer data, or confidential discussions, creating medium severity risk if an AI agent retrieves and exfiltrates transcripts without authorization. The read-only nature and lack of side effects place it in the Read category.
From the tool's definition Tool name 'ms_transcripts' and description 'Fetch meeting transcripts from Microsoft Teams' indicate a retrieval operation. Server description explicitly states 'read-only access' to meeting transcripts.
Attacks that exploit this kind of access
Fetch meeting transcripts from Microsoft Teams. 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_transcripts: 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_transcripts 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_transcripts 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_transcripts. 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_transcripts 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 →