AI agents call api_features 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 retrieves configuration or feature flag data from a Slack workspace without modifying it, placing it in the Read category. Severity is medium because: (1) feature flags may reveal internal system configuration, experimental features, or security settings that could inform attack surface mapping; (2) access is via an undocumented endpoint, suggesting it may bypass normal authorization patterns; (3) the…
From the tool's definition Tool name 'api_features' and description state it 'Get[s] workspace feature flags' — a retrieval operation with no modification or deletion. The description characterizes it as an 'undocumented session endpoint', indicating internal/privileged data access.
Attacks that exploit this kind of access
Get workspace feature flags (undocumented session endpoint). 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_features: 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_features 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_features 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_features. 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_features 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 →