AI agents use unset_channel_message_reaction to create or update resources in Teams — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Teams environment.
Removing a reaction is a reversible modification to a message (reactions can be re-added). It does not delete content, execute code, or have financial impact. It modifies state but in a minor, reversible way, making it a Write action with low severity.
From the tool's definition Remove a reaction from a message in a Teams channel. Can also remove reactions from replies.
Attacks that exploit this kind of access
Remove a reaction from a message in a Teams channel. Can also remove reactions from replies. It is categorised as a Write tool in the Teams MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Teams MCP server in PolicyLayer and add a rule for unset_channel_message_reaction: 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. Nothing to install.
unset_channel_message_reaction 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 unset_channel_message_reaction 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 unset_channel_message_reaction. 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.
unset_channel_message_reaction is provided by the Teams MCP server (@floriscornel/teams-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.