slack_add_reaction
AI agents use slack_add_reaction to create or update resources in Integrations MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Integrations MCP environment.
Adding a reaction is a reversible modification operation that changes Slack message metadata without deleting or destroying data. While the empty description reduces confidence slightly, the tool name clearly indicates a write-like action. Severity is low because reactions are non-critical metadata and misuse would have minimal impact (adding unwanted emoji reactions).
From the tool's definition Tool name 'slack_add_reaction' indicates it adds a reaction to a message, which modifies Slack's state by attaching an emoji/reaction to a message.
Attacks that exploit this kind of access
slack_add_reaction. It is categorised as a Write tool in the Integrations MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Integrations MCP server in PolicyLayer and add a rule for slack_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 Integrations MCP. Nothing to install.
slack_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 slack_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 slack_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.
slack_add_reaction is provided by the Integrations MCP server (shriram-vasudevan/integrations-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 →