Launch the browser, navigate to /feed/, confirm authentication.
AI agents invoke session_warmup to trigger actions in Linkedin Company Admin. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes browser actions (launching a browser and navigating to a URL) to establish or verify an authenticated session. It triggers external operations with side effects beyond simple data retrieval, fitting the Execute category. Misuse could expose session state or authentication tokens, warranting medium severity.
From the tool's definition Launch the browser, navigate to /feed/, confirm authentication
Attacks that exploit this kind of access
Launch the browser, navigate to /feed/, confirm authentication. It is categorised as a Execute tool in the Linkedin Company Admin MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Linkedin Company Admin MCP server in PolicyLayer and add a rule for session_warmup: 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 Company Admin. Nothing to install.
session_warmup is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the session_warmup 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 session_warmup. 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.
session_warmup is provided by the Linkedin Company Admin MCP server (negrueu/linkedin-company-admin-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 →