Setting up the agent

The demo needs an AI client with two things wired up: a model reached through Cloudflare AI Gateway, and the four MCP servers reached through the MCP server portal. These are the two places the controls live.

You need three values

Your Cloudflare account ID.
The AI Gateway id — ai-demo unless you changed AI_GATEWAY_ID in config.sh.
A Cloudflare API token with Workers AI read access, used as the API key.

The portal lives at and the individual MCP servers at , , and .

Sign in as the right person

Every demo is run as Delta Graham — delta.graham@company.com, password Savetheinternet!1. When the agent connects to the portal you will be sent through Cloudflare Access and then FlareID; log in as Delta, not as the admin account. The whole point is that the agent is acting with a real, low-privilege identity.

Option A — opencode

Add a provider pointing at AI Gateway's OpenAI-compatible endpoint and an MCP entry pointing at the portal. In ~/.config/opencode/opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "cloudflare-ai-gateway": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Cloudflare AI Gateway",
      "options": {
        "baseURL": "https://gateway.ai.cloudflare.com/v1/<ACCOUNT_ID>/ai-demo/compat",
        "apiKey": "<CLOUDFLARE_API_TOKEN>"
      },
      "models": {
        "workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast": {
          "name": "Llama 3.3 70B (Workers AI)"
        }
      }
    }
  },
  "mcp": {
    "ai-demo": {
      "type": "local",
      "command": ["npx", "-y", "mcp-remote@latest", "https://mcp.<ZONE>/mcp"],
      "enabled": true
    }
  }
}

mcp-remote handles the portal's OAuth flow and opens a browser window for the Access login. If your opencode build supports remote MCP servers with OAuth directly, you can use { "type": "remote", "url": "https://mcp.<ZONE>/mcp" } instead.

Option B — Open WebUI

Model. Settings → Connections → add an OpenAI-compatible connection with base URL https://gateway.ai.cloudflare.com/v1/<ACCOUNT_ID>/ai-demo/compat and your Cloudflare API token as the key. Use the model id workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast.
Tools. Bridge the MCP portal to an OpenAPI tool server and add it under Settings → Tools:
uvx mcpo --port 8000 -- npx -y mcp-remote@latest https://mcp.<ZONE>/mcp
Recent Open WebUI builds can also add a streamable-HTTP MCP server directly; either path works, the portal does not care.
Access. Open WebUI itself sits behind its own Cloudflare Access application with SSO, so the person typing prompts is already authenticated before they reach it.

Running without the protection layer first

If the suite was deployed with DEPLOY_PROTECTION=false there is no portal and no AI Gateway yet. Point the client at the four MCP servers individually and at the model provider directly:

{
  "mcp": {
    "workweek": { "type": "local", "command": ["npx", "-y", "mcp-remote@latest", "https://hr-mcp.<ZONE>/mcp"] },
    "pipeline": { "type": "local", "command": ["npx", "-y", "mcp-remote@latest", "https://crm-mcp.<ZONE>/mcp"] },
    "relay":    { "type": "local", "command": ["npx", "-y", "mcp-remote@latest", "https://work-mcp.<ZONE>/mcp"] },
    "nexus":    { "type": "local", "command": ["npx", "-y", "mcp-remote@latest", "https://wiki-mcp.<ZONE>/mcp"] }
  }
}

Each server runs its own OAuth 2.1 flow and delegates login to Cloudflare Access, so you will sign in as Delta once per server. Every demo script works in this mode — that is the "before" half of each one.

Tool names change when you go through the portal

The portal namespaces every tool with its server id, so list_employees becomes hr_list_employees, get_pipeline_summary becomes crm_get_pipeline_summary, and so on with work_ and wiki_. The demo scripts name the underlying tool; your transcript will show the prefixed one.

Check it works

Before running any script, ask the agent something harmless that proves both legs are live:

Who am I, and which tools do you have available?

You should see Delta Graham come back from the whoami tool, a list of tools from all four servers, and — if the protection layer is deployed — a corresponding request in the AI Gateway log and in the MCP portal log.