AI agents use emoji_add to create or update resources in Slack — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Slack environment.
This tool creates (adds) a new custom emoji resource, which is a reversible write operation. While it modifies Slack workspace configuration, the action can be undone by deleting the emoji. The use of an 'undocumented session endpoint' adds some concern about stability but does not elevate it to Execute (no arbitrary code execution) or Destructive (emoji creation is reversible).
From the tool's definition Tool name 'emoji_add' and description 'Add a custom emoji from a URL' indicate creation of new custom emoji resources in Slack.
Attacks that exploit this kind of access
Add a custom emoji from a URL (undocumented session endpoint). It is categorised as a Write tool in the Slack MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Slack MCP server in PolicyLayer and add a rule for emoji_add: 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 Slack. Nothing to install.
emoji_add 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 emoji_add 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 emoji_add. 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.
emoji_add is provided by the Slack MCP server (karbassi/slack-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 →