API Keys have various scopes permissions and belong to a specific Team or Environment. Use this to validate authentication for a key, to determine what authorizations have been granted to a key, and to determine the Team and Environment that a key belongs to.
AI agents call honeycomb_auth to retrieve information from Honeycomb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
honeycomb_auth retrieves metadata about API key authorization state and scope permissions. This is fundamentally a read operation (query). However, severity is high because the tool exposes sensitive authorization and credential metadata that could inform privilege escalation or lateral movement attacks if misused by an agent to enumerate team/environment access.
From the tool's definition Tool validates authentication and determines key scopes/permissions/team/environment. Language indicates query/inspection only: 'validate', 'determine'. No modification or side effects.
Attacks that exploit this kind of access
API Keys have various scopes permissions and belong to a specific Team or Environment. Use this to validate authentication for a key, to determine what authorizations have been granted to a key, and to determine the Team and Environment that a key belongs to. It is categorised as a Read tool in the Honeycomb MCP Server, which means it retrieves data without modifying state.
Register the Honeycomb MCP server in PolicyLayer and add a rule for honeycomb_auth: 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 Honeycomb. Nothing to install.
honeycomb_auth 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 honeycomb_auth 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 honeycomb_auth. 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.
honeycomb_auth is provided by the Honeycomb MCP server (kajirita2002/honeycomb-mcp-server). 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 →