teams_read_chat_messages
Reads messages from a Teams chat or direct message thread.
This record as markdown: /tools/com-local-mcp-local-mcp/teams-read-chat-messages.md
What teams_read_chat_messages does on Local
AI agents call teams_read_chat_messages to retrieve information from Local without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | integer | — | Max messages (default 50) |
chat_id | string | Yes | Chat ID from list_teams_chats |
Parameters from the server's own tool schema.
Why teams_read_chat_messages is rated Low
This is a read-only operation that retrieves existing chat messages. It has no side effects on data. However, severity is elevated to medium rather than low because Teams messages may contain sensitive information (PII, business secrets, credentials), and an AI agent with uncontrolled access could exfiltrate confidential communications at scale.
From the tool's definition Tool name explicitly includes 'read' and description states 'Reads messages from a Teams chat or direct message thread' — a data retrieval operation with no modification, creation, or deletion.
Attacks that exploit this kind of access
The rule that runs teams_read_chat_messages safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Local, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For teams_read_chat_messages, this is the rule to start with:
teams_read_chat_messages is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Local, apply this rule, and every teams_read_chat_messages call is checked against it from then on.
Questions about teams_read_chat_messages
Reads messages from a Teams chat or direct message thread. It is categorised as a Read tool in the Local MCP Server, which means it retrieves data without modifying state.
teams_read_chat_messages accepts 2 parameters: limit, chat_id. Required: chat_id. The full parameter table on this page comes from the server's own tool schema.
Register the Local MCP server in PolicyLayer and add a rule for teams_read_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 Local. Nothing to install.
teams_read_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_read_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_read_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_read_chat_messages is provided by the Local MCP server (local-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Local, and thousands of servers like it.
This server
Across the catalogue