KINETK
// Easy Start Guide

Connect KINETK to your AI assistant

With one quick setup, you can connect KINETK to the AI assistant you already use — Claude, ChatGPT, Cursor, and others. Once connected, just talk to your assistant in plain English, and mention “kinetk” when you want live intelligence.

// Pick your assistant

Quick setup examples - choose the one you already use.

[ Desktop App ]

Claude Desktop

Add KINETK as a custom connector inside the Claude app.

  1. 1Open Settings → Connectors → Add custom connector.
  2. 2Paste the sign-in address below into the connector URL field.
  3. 3Save, then click Connect / Sign in — a browser opens to the KINETK login. Sign in and approve.
  4. 4KINETK shows as connected, and the tools appear near the message box.
Sign-in address
https://api.kinetk.ai/graph/connect

Claude Code

Register the KINETK MCP server from your terminal.

  1. 1Run the command below, replacing YOUR_KEY with your KINETK API key.
  2. 2Restart Claude Code — the kinetk tools load automatically.
Terminal
claude mcp add --transport http kinetk https://api.kinetk.ai/graph/mcp --header "x-api-key: YOUR_KEY"
[ Web App ]

ChatGPT

Add KINETK as app inside ChatGPT on the web.

  1. 1Open ChatGPT on the web. This setup isn't available in the mobile or desktop apps, and requires a paid ChatGPT plan.
  2. 2Go to Settings → Apps → Advanced settings and turn Developer mode on.
  3. 3Click Create App, paste the sign-in address below, then click Create.
  4. 4Sign in with KINETK and tools are ready.
Sign-in address
https://api.kinetk.ai/graph/connect

Codex

Add the KINETK MCP server to your Codex config.

  1. 1Open ~/.codex/config.toml on Linux/macOS ($HOME/.codex/config.toml on Windows).
  2. 2Add the config below to the bottom of the file.
  3. 3Replace the “API_KEY” placeholder with your KINETK API key.
  4. 4Start Codex and verify with the /mcp command.
config.toml
[mcp_servers.kinetk]
url = "https://api.kinetk.ai/graph/mcp"
enabled = true
startup_timeout_sec = 30

[mcp_servers.kinetk.http_headers]
"x-api-key" = "API_KEY"

Cursor

Add KINETK under Tools & MCPs in Cursor settings.

  1. 1Open Settings → Tools & MCP → New MCP Server or Add Custom MCP.
  2. 2Paste the JSON below to the mcp.json
  3. 3Change the “api-key” placeholder with your KINETK API key.
  4. 4Refresh — the kinetk tools become available.
JSON
{ "mcpServers": { "kinetk": { "command": "npx", "args": [ "-y", "mcp-remote", "https://api.kinetk.ai/graph/mcp", "--header", "x-api-key:${KINETK_KEY}" ], "env": { "KINETK_KEY": "api-key" } } } }

Gemini/Antigravity

Add the KINETK MCP server to your Gemini config.

  1. 1Open ~/.gemini/config/mcp_config.json on macOS ($HOME/.gemini/config/mcp_config.json on Windows).
  2. 2Paste the JSON below into the file.
  3. 3Replace the “API_KEY” placeholder with your KINETK API key.
  4. 4Launch Antigravity (agy) and verify with the /mcp command.
JSON
{
  "mcpServers": {
    "kinetk": {
      "serverUrl": "https://api.kinetk.ai/graph/mcp",
      "headers": {
        "x-api-key": "API_KEY"
      }
    }
  }
}

Grok

Register the KINETK MCP server from your terminal.

  1. 1Run the commands below for your OS, replacing API_KEY with your KINETK API key.
  2. 2Start Grok and verify with the /mcp command.
macOS / Linux
export KINETK_API_KEY="API_KEY"
grok mcp add --transport http kinetk https://api.kinetk.ai/graph/mcp --header "x-api-key: ${KINETK_API_KEY}"
Windows
$env:KINETK_API_KEY="API_KEY"
grok mcp add --transport http kinetk https://api.kinetk.ai/graph/mcp --header "x-api-key: $env:KINETK_API_KEY"