list_reactions
AI agents call list_reactions to retrieve information from Slack MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or enumerates reactions from Slack messages or threads. It has no side effects—it queries existing data. Even if misused, an agent can only read reaction metadata, posing minimal risk. The low severity reflects that exposure of reaction data is typically non-sensitive compared to financial, destructive, or execution operations.
From the tool's definition Tool name 'list_reactions' indicates a retrieval operation. Sibling tools on this server follow a clear pattern where 'list_' and 'get_' prefixes denote read-only operations (list_channels, list_files, get_channel_history, get_user_info, etc.).
Attacks that exploit this kind of access
list_reactions. It is categorised as a Read tool in the Slack MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Slack MCP Server MCP server in PolicyLayer and add a rule for list_reactions: 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 MCP Server. Nothing to install.
list_reactions is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_reactions 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 list_reactions. 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.
list_reactions is provided by the Slack MCP Server MCP server (software-engineer-mj/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 →