Get an ID token for a user in the Auth emulator. Lists users if no uid provided.
AI agents call get_auth_token to retrieve information from Firebase MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves authentication tokens and lists users from the emulator environment. While tokens are sensitive, this is a Read operation within an emulator context with no irreversible side effects. It does not execute arbitrary code, modify data, delete anything, or move financial resources. The emulator environment limits real-world impact.
From the tool's definition Tool description states 'Get an ID token for a user in the Auth emulator. Lists users if no uid provided.' This is a retrieval operation that queries existing authentication state without modifying or deleting data.
Attacks that exploit this kind of access
Get an ID token for a user in the Auth emulator. Lists users if no uid provided. It is categorised as a Read tool in the Firebase MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Firebase MCP Server MCP server in PolicyLayer and add a rule for get_auth_token: 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 Firebase MCP Server. Nothing to install.
get_auth_token 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 get_auth_token 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 get_auth_token. 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.
get_auth_token is provided by the Firebase MCP Server MCP server (nigelthorne/firebase_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 →