Add a reaction emoji to a message
AI agents use mattermost_add_reaction to create or update resources in Mattermost — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mattermost environment.
Adding a reaction is a reversible write operation that creates or associates data (emoji reaction) with a message. It is not destructive, does not execute arbitrary code, involves no financial impact, and is not a read-only query. The blast radius is minimal as reactions are low-stakes metadata on messages. Severity is low because reaction spam has limited real-world impact compared to other message operations.
From the tool's definition Tool description states 'Add a reaction emoji to a message' — this creates a new reaction object/association on an existing message, modifying the message's metadata reversibly.
Attacks that exploit this kind of access
Add a reaction emoji to a message. It is categorised as a Write tool in the Mattermost MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mattermost MCP server in PolicyLayer and add a rule for mattermost_add_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 Mattermost. Nothing to install.
mattermost_add_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 mattermost_add_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 mattermost_add_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.
mattermost_add_reaction is provided by the Mattermost MCP server (@conarti/mattermost-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 →