Skip to main content
FloKit connects to OpenAI two ways: as a connector in ChatGPT (sign in with OAuth), or as an MCP tool from the OpenAI API (Responses API or Agents SDK) with an access token. Same read-only server, same tools.

Server URL

https://api.dashboard.flokitai.com/mcp

​
Option A — ChatGPT Developer Mode connector

Custom MCP connectors live under Developer Mode, available on ChatGPT Plus, Pro, Business, and Enterprise. Enable it in Settings → Connectors → Advanced → Developer mode.
1

Create a new connector

In Settings → Connectors, choose New connector (Developer Mode). Name it FloKit and paste the server URL, with authentication set to OAuth.
ChatGPT new connector dialog with the FloKit MCP URL and OAuth
2

Sign in and approve

ChatGPT opens the FloKit consent screen. Sign in with your FloKit work email and click Allow access — the screen confirms read-only access.
FloKit OAuth consent screen granting status:read
3

Ask FloKit something

Start a chat with the FloKit connector enabled and try:
What's waiting for my approval, and what's my MRR this month?

​
Option B — OpenAI API (Responses / Agents)

Point the OpenAI Responses API MCP tool at FloKit and pass your access token as the authorization value — no browser sign-in.
1

Create an access token in FloKit

In the dashboard, Settings → Connected assistants → Create. Copy the token (starts with flk_live_).
FloKit dashboard connected assistants panel with server URL and access token
2

Call it as an MCP tool

from openai import OpenAI

client = OpenAI()

resp = client.responses.create(
    model="gpt-5",  # any model that supports MCP tools
    tools=[{
        "type": "mcp",
        "server_label": "flokit",
        "server_url": "https://api.dashboard.flokitai.com/mcp",
        "authorization": "flk_live_your_token_here",
        "require_approval": "never",  # all FloKit tools are read-only
    }],
    input="What's going on with my app, and is anything waiting on my approval?",
)

print(resp.output_text)

import OpenAI from "openai";

const client = new OpenAI();

const resp = await client.responses.create({
  model: "gpt-5", // any model that supports MCP tools
  tools: [{
    type: "mcp",
    server_label: "flokit",
    server_url: "https://api.dashboard.flokitai.com/mcp",
    authorization: "flk_live_your_token_here",
    require_approval: "never", // all FloKit tools are read-only
  }],
  input: "What's going on with my app, and is anything waiting on my approval?",
});

console.log(resp.output_text);
Because every FloKit tool is read-only, require_approval: "never" is safe — the model can’t trigger a side effect. Keep the token server-side; never ship it to a browser or mobile client.

​
Troubleshooting

The token was revoked or expired. Mint a fresh one in Settings → Connected assistants.
Make sure your prompt asks for something FloKit knows — status, metrics, or approvals. Vague prompts may not trigger a tool call; try one of the example prompts.