Remove a conversation from the user\
AI agents use teams_remove_favorite to create or update resources in Teams MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Teams MCP Server environment.
Removing a favorite is a reversible write operation (the user can re-add the conversation as a favorite). It does not delete any messages or data, just modifies a user preference/bookmark list. Severity is low as the blast radius is minimal — at worst a conversation is unfavorited and can be re-added.
From the tool's definition 'Remove a conversation from the user' favorites/followed list — reverses the teams_add_favorite action
Attacks that exploit this kind of access
Remove a conversation from the user\. It is categorised as a Write tool in the Teams MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Teams MCP Server MCP server in PolicyLayer and add a rule for teams_remove_favorite: 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_remove_favorite is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the teams_remove_favorite 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_remove_favorite. 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_remove_favorite 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 →