AI agents call api_test 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.
This tool appears to be a testing/validation utility that inspects API calling code for correctness. It does not retrieve data from Slack, modify any state, execute commands, or trigger destructive actions. It's a read-only diagnostic tool. Severity is low because even if misused, it can only validate code, not cause side effects.
From the tool's definition Tool description states 'Check API calling code. Helps test your calling code.' — this is a diagnostic/validation function that tests code without executing it against live data or systems. It reads and validates calling code.
Attacks that exploit this kind of access
Check API calling code. Helps test your calling code. 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 api_test: 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.
api_test 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 api_test 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 api_test. 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.
api_test 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 →