This record as markdown: /tools/karbassi-slack-mcp/reactions-add.md
What reactions_add does on Slack
AI agents use reactions_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.
Why reactions_add is rated Medium
Adding a reaction creates new data (the reaction association) and modifies the state of a Slack item, making it a Write operation rather than Read. The severity is medium because while reversible (reactions can be removed), it could be used to manipulate conversations, spam reactions, or harass users at scale if abused.
From the tool's definition Tool name 'reactions_add' and description 'Add a reaction to an item' indicate creation of a new reaction object/state in Slack. This modifies data by adding metadata (emoji reaction) to a message or other item.
Attacks that exploit this kind of access
The rule that runs reactions_add safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Slack, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For reactions_add, this is the rule to start with:
reactions_add stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Slack, apply this rule, and every reactions_add call is checked against it from then on.
Questions about reactions_add
Add a reaction to an item. 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 reactions_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.
reactions_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 reactions_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 reactions_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.
reactions_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.
More on Slack, and thousands of servers like it.
This server
Across the catalogue