AI agents call assistant_search_context to retrieve information from Slack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool name 'assistant_search_context' and the server's documented search capabilities, this appears to be a Read operation that retrieves contextual data for assistants. The 'search' verb indicates data retrieval without modification. Severity is high because search tools on communication platforms can expose sensitive message content, user information, and organizational data if misused by an AI agent.
From the tool's definition Tool name contains 'search' and 'context', suggesting it retrieves or queries data. Server description confirms the tool is part of Slack's 220 tools providing access to messages, channels, and search functionality.
Attacks that exploit this kind of access
assistant_search_context. It is categorised as a Read tool in the Slack MCP Server, which means it retrieves data without modifying state.
Register the Slack MCP server in PolicyLayer and add a rule for assistant_search_context: 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.
assistant_search_context 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 assistant_search_context 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 assistant_search_context. 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.
assistant_search_context 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 →