Get the conversation ID for a 1:1 chat with a person. Use this to start a new chat or find an existing one. The conversation ID can then be used with teams_send_message to send messages.
AI agents call teams_get_chat to retrieve information from Teams MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata (conversation ID) about existing chats without creating, modifying, deleting, or executing any operations. It is purely informational and serves as a lookup mechanism to enable subsequent actions. The severity is low because merely obtaining a conversation ID poses minimal risk—the ID itself is not sensitive data and cannot be misused without additional tools like teams_send_message.
From the tool's definition Tool description explicitly states 'Get the conversation ID' and is designed to 'find an existing one' chat. The verb 'Get' and the read-only nature of retrieving a conversation identifier indicate a query operation with no side effects.
Attacks that exploit this kind of access
Get the conversation ID for a 1:1 chat with a person. Use this to start a new chat or find an existing one. The conversation ID can then be used with teams_send_message to send messages. It is categorised as a Read tool in the Teams MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Teams MCP Server MCP server in PolicyLayer and add a rule for teams_get_chat: 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 Teams MCP Server. Nothing to install.
teams_get_chat 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 teams_get_chat 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 teams_get_chat. 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.
teams_get_chat is provided by the Teams MCP Server MCP server (m0nkmaster/msteams-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 →