AI agents call teams_chat_messages to retrieve information from Outpost without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves existing chat messages from Microsoft Teams without creating, modifying, deleting, or executing any actions. It is a straightforward read-only operation that has no side effects on data or system state. The severity is low because message retrieval poses minimal risk even if misused by an agent — it does not alter data, trigger external operations, or expose financial systems.
From the tool's definition Tool name and description explicitly state 'Read messages from a Teams chat' — a retrieval operation with no modification, deletion, or execution of code/commands.
Attacks that exploit this kind of access
Read messages from a Teams chat (1:1 or group). It is categorised as a Read tool in the Outpost MCP Server, which means it retrieves data without modifying state.
Register the Outpost MCP server in PolicyLayer and add a rule for teams_chat_messages: 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 Outpost. Nothing to install.
teams_chat_messages 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_chat_messages 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_chat_messages. 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_chat_messages is provided by the Outpost MCP server (signalclaude/outpost). 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 →