Use this when ChatGPT needs OAuth token session metadata.
AI agents call auth.session to retrieve information from GPT MCP Service without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves session metadata related to OAuth tokens. While it accesses authentication-sensitive information (OAuth tokens), it is fundamentally a read operation that queries existing data without modifying it.
From the tool's definition Tool description states it provides 'OAuth token session metadata' - a retrieval operation with no modification capability. The word 'metadata' and the phrase 'Use this when ChatGPT needs' indicate data querying.
Attacks that exploit this kind of access
Use this when ChatGPT needs OAuth token session metadata. It is categorised as a Read tool in the GPT MCP Service MCP Server, which means it retrieves data without modifying state.
Register the GPT MCP Service MCP server in PolicyLayer and add a rule for auth.session: 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 GPT MCP Service. Nothing to install.
auth.session 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 auth.session 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 auth.session. 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.
auth.session is provided by the GPT MCP Service MCP server (jmillpps/encore-mcp-base). 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 →