AI agents call slack_search_messages to retrieve information from MCP Slack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches messages in Slack, which is a read-only operation that retrieves information without side effects. The server is explicitly described as 'read-only' and all sibling tools perform only retrieval operations (list, get), establishing a pattern. Even with an empty description, the tool name and ecosystem context provide strong evidence this is a Read operation with minimal blast radius.
From the tool's definition Tool name 'slack_search_messages' and server context ('Secure read-only MCP server for Slack workspaces') both indicate data retrieval without modification. All sibling tools are read operations (get_*, list_*).
Attacks that exploit this kind of access
slack_search_messages. It is categorised as a Read tool in the MCP Slack MCP Server, which means it retrieves data without modifying state.
Register the MCP Slack MCP server in PolicyLayer and add a rule for slack_search_messages: 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 MCP Slack. Nothing to install.
slack_search_messages 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 slack_search_messages 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_search_messages. 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_search_messages is provided by the MCP Slack MCP server (pypi:mcp-slack-crunchtools). 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 →