AI agents call linkedin_oauth_get_auth_url to retrieve information from Linkedin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
OAuth URL generation is a read-only operation with no side effects. It retrieves/constructs an authentication endpoint URL without modifying data, executing code, or performing destructive actions. The tool enables the authentication flow but does not itself authenticate, create resources, or make changes. Severity is low because misuse would only expose a URL string, not credentials or sensitive data.
From the tool's definition Tool name is 'linkedin_oauth_get_auth_url' and description states it 'Generate[s] OAuth 2.0 authorization URL for LinkedIn authentication'. This is a pure information retrieval operation that generates a URL string for authentication flow initiation.
Attacks that exploit this kind of access
Generate OAuth 2.0 authorization URL for LinkedIn authentication. It is categorised as a Read tool in the Linkedin MCP Server, which means it retrieves data without modifying state.
Register the Linkedin MCP server in PolicyLayer and add a rule for linkedin_oauth_get_auth_url: 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 Linkedin. Nothing to install.
linkedin_oauth_get_auth_url 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 linkedin_oauth_get_auth_url 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 linkedin_oauth_get_auth_url. 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.
linkedin_oauth_get_auth_url is provided by the Linkedin MCP server (maheidem/linkedin-optimizer-mcp). 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 →