AI & Data
xAI / Grok
Provides the Grok large language model API from xAI for reasoning and conversational tasks.
Connect stays on CybrLink. Signed-out visitors go to sign-in. Signed-in visitors open the connect host at connect.cybrlink.dev.
API keyScoped proxy
Connect with a provider API key
The client enters their provider key in the hosted connect flow. CybrLink stores it in the credential layer, then agents call through scoped MCP/API access without seeing the raw secret.
Where to get your xAI / Grok API keyStep 1
Open the portal connect flow
Step 2
Enter the provider API key
Step 3
Create a scoped MCP/API key
Sample request
// 1. Mint a session token for the end user
const session = await link.connect.session({
integrationKey: "xai",
userId: "u_42",
});
// 2. After the user enters their provider API key, proxy a request
const res = await link.proxy("xai", "u_42", {
method: "GET",
endpoint: "/api/v1/me",
});More in this category
Typed agent tools
Typed MCP tool schemas are not published for xAI / Grok yet. Connecting still lets an agent call this integration through CybrLink's scoped proxy. This page does not list a tool count until those schemas exist.
xAI / Grok + SI (super intelligence) agents: common questions
- How do I connect xAI / Grok to an SI agent?
- Create a free CybrLink account, open the dashboard, and click Connect on xAI / Grok. You authorize once with an API key; CybrLink stores the credential in its token vault and your agent reaches xAI / Grok through the CybrLink MCP server or the agent proxy API. The credential itself is never placed in the model's context.
- Does xAI / Grok work with Claude, GPT, and other MCP clients?
- Yes. CybrLink exposes a remote MCP (Model Context Protocol) server, so any MCP-capable client or agent framework — including Claude, OpenAI-based agents, and custom agents — can call xAI / Grok once you've connected it. Non-MCP agents can use the authenticated HTTP proxy instead.
- Is it safe to give an SI agent access to xAI / Grok?
- CybrLink scopes every connection to the permissions you grant, keeps tokens out of the model, logs each call to an activity audit trail, and lets you revoke the xAI / Grok connection at any time from the dashboard.