Get detailed Azure OAuth2 token information including expiry.
AI agents call get_azure_token_info to retrieve information from OAuth MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads token information but does not create, modify, execute code, delete data, or move money. However, the retrieved token information is sensitive authentication data that could be misused if exposed to a malicious actor, warranting medium severity.
From the tool's definition Tool description states 'Get detailed Azure OAuth2 token information including expiry' — this retrieves and queries token metadata without modifying or executing operations. The action is read-only retrieval of authentication token details.
Attacks that exploit this kind of access
Get detailed Azure OAuth2 token information including expiry. It is categorised as a Read tool in the OAuth MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OAuth MCP Server MCP server in PolicyLayer and add a rule for get_azure_token_info: 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 OAuth MCP Server. Nothing to install.
get_azure_token_info 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_azure_token_info 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_azure_token_info. 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_azure_token_info is provided by the OAuth MCP Server MCP server (walkerpauldavid/oauth_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 →