Return OAuth status for an approval_id or current connection status.
AI agents call auth_status to retrieve information from AIOS Co-Founder MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the current authentication/authorization state without side effects. It retrieves information about OAuth connectivity status for a given approval_id or current session, similar to a status check or health probe. No data is modified, no operations are triggered, and no external services are invoked. This is a straightforward Read operation with minimal risk if disclosed to an agent.
From the tool's definition Tool name is 'auth_status' and description states it 'Return[s] OAuth status' — a retrieval operation with no modification, creation, deletion, or execution of external actions. Returns current connection state only.
Attacks that exploit this kind of access
Return OAuth status for an approval_id or current connection status. It is categorised as a Read tool in the AIOS Co-Founder MCP MCP Server, which means it retrieves data without modifying state.
Register the AIOS Co-Founder MCP server in PolicyLayer and add a rule for auth_status: 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 AIOS Co-Founder MCP. Nothing to install.
auth_status 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_status 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_status. 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_status is provided by the AIOS Co-Founder MCP server (varun-b-nagaraj/python-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 →