> ## Documentation Index
> Fetch the complete documentation index at: https://developers.everflow.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Connect an MCP-compatible AI client to your Everflow network in under 5 minutes.

<Warning>
  **MCP must be enabled for your network** before any connection attempt will succeed. Email [support@everflow.io](mailto:support@everflow.io) to request access. See the [Overview](/ai-automation/mcp/overview) for full availability details.
</Warning>

<Tip>
  **EU Cluster Support:** If your Everflow account is hosted in the EU, simply replace `https://mcp.eflow.team` with `https://mcp-eu.eflow.team` in any of the configuration examples below.
</Tip>

## Prerequisites

* A **Network API key** with access to your network. See [Authentication](/user-guide/authentication).
* MCP access enabled for your network (see the [Overview](/ai-automation/mcp/overview) for server URL, transport, and availability details).

***

## Connect your client

Each setup takes under 5 minutes. Depending on where your account is hosted, choose the appropriate server URL:

* **US-Hosted Accounts:** `https://mcp.eflow.team`
* **EU-Hosted Accounts:** `https://mcp-eu.eflow.team`

All clients authenticate with the `X-Eflow-API-Key` header — the config format varies by client, and some clients like Claude.ai web don't support API-key headers at all.

**If you're unsure where to start, use Claude Desktop** — it has the most straightforward setup and the best out-of-the-box MCP experience.

<Tabs>
  <Tab title="Claude Desktop">
    <Steps>
      <Step title="Open your Claude Desktop config file">
        ```bash macOS theme={null}
        open ~/Library/Application\ Support/Claude/claude_desktop_config.json
        ```

        ```bash Windows theme={null}
        notepad %APPDATA%\Claude\claude_desktop_config.json
        ```
      </Step>

      <Step title="Add the Everflow server to the mcpServers block">
        ```json theme={null}
        {
          "mcpServers": {
            "everflow": {
              "command": "npx",
              "args": [
                "-y",
                "mcp-remote",
                "https://mcp.eflow.team",
                "--header",
                "X-Eflow-API-Key:your-network-api-key"
              ]
            }
          }
        }
        ```

        <Note>
          Claude Desktop currently requires the `mcp-remote` stdio bridge to connect to remote MCP servers. The `npx -y` prefix auto-installs the package on first launch — no separate install step is needed. For the latest on native remote MCP support in Claude Desktop, see [Anthropic's changelog](https://www.anthropic.com/changelog).
        </Note>

        <Tip>
          The `--header` value uses `Name:Value` with **no space** after the colon. `X-Eflow-API-Key: your-network-api-key` (with a space) will fail.
        </Tip>
      </Step>

      <Step title="Save the file and restart Claude Desktop">
        Quit and reopen the app so it picks up the new MCP server.
      </Step>

      <Step title="Test the connection">
        Open a new conversation. You should see an Everflow tools indicator in the input area. Ask:

        > "What is my network's name and default currency?"
      </Step>
    </Steps>
  </Tab>

  <Tab title="Claude Code">
    [Claude Code](https://docs.claude.com/en/docs/claude-code) is Anthropic's CLI agent, with native support for remote MCP servers over HTTP.

    <Steps>
      <Step title="Add the Everflow server">
        ```bash theme={null}
        claude mcp add --transport http everflow https://mcp.eflow.team \
          --header "X-Eflow-API-Key: your-network-api-key"
        ```
      </Step>

      <Step title="Verify the connection">
        Run `/mcp` inside Claude Code to confirm the `everflow` server is connected, then ask:

        > "Call get\_account\_info and tell me my network name and default currency."
      </Step>
    </Steps>
  </Tab>

  <Tab title="Claude.ai">
    <Warning>
      **Claude.ai web doesn't support API-key headers.** Its connector UI is OAuth-only, and Everflow MCP authenticates with the `X-Eflow-API-Key` header — there's no field for it. Use **Claude Desktop**, **Claude Code**, or **Cursor** instead.
    </Warning>

    Anthropic has marked header support for the Claude.ai connector UI as [not planned](https://github.com/anthropics/claude-ai-mcp/issues/110). Until that changes, connect through one of the other clients in the tabs above.
  </Tab>

  <Tab title="Cursor">
    <Steps>
      <Step title="Open Cursor's MCP settings">
        Go to **Cursor Settings → MCP**, or press `Cmd+Shift+P` → `MCP: Edit Configuration`.
      </Step>

      <Step title="Add the Everflow server">
        ```json theme={null}
        {
          "mcpServers": {
            "everflow": {
              "url": "https://mcp.eflow.team",
              "headers": {
                "X-Eflow-API-Key": "your-network-api-key"
              }
            }
          }
        }
        ```

        <Warning>
          This config holds your network API key in plaintext. If it lives in a workspace `.cursor/mcp.json`, add it to `.gitignore` so the key never lands in a committed repo.
        </Warning>
      </Step>

      <Step title="Save and reload the window">
        The Everflow tools will appear in the Cursor Agent chat.
      </Step>
    </Steps>
  </Tab>

  <Tab title="Gemini CLI">
    [Gemini CLI](https://github.com/google-gemini/gemini-cli) is Google's open-source terminal agent with native MCP support.

    <Steps>
      <Step title="Install Gemini CLI">
        ```bash theme={null}
        npm install -g @google/gemini-cli
        ```
      </Step>

      <Step title="Open the Gemini CLI config file">
        ```bash theme={null}
        open ~/.gemini/settings.json
        ```

        Create the file if it doesn't exist yet.
      </Step>

      <Step title="Add the Everflow server">
        ```json theme={null}
        {
          "mcpServers": {
            "everflow": {
              "httpUrl": "https://mcp.eflow.team",
              "headers": {
                "X-Eflow-API-Key": "your-network-api-key"
              }
            }
          }
        }
        ```
      </Step>

      <Step title="Start a session and verify the connection">
        ```bash theme={null}
        gemini
        ```

        > "Call get\_account\_info and tell me my network name and default currency."
      </Step>
    </Steps>
  </Tab>

  <Tab title="VS Code">
    <Warning>
      VS Code requires an active **GitHub Copilot Chat** subscription and the [Copilot Chat extension](https://marketplace.visualstudio.com/items?itemName=GitHub.copilot-chat). The config format also differs from the other clients — note the `servers` key instead of `mcpServers`.
    </Warning>

    <Steps>
      <Step title="Install the GitHub Copilot Chat extension">
        Install it from the VS Code marketplace if you don't have it already.
      </Step>

      <Step title="Open your MCP configuration">
        Open VS Code settings (`Cmd+,`) and search for **MCP Servers**, or edit `.vscode/mcp.json` directly in your workspace:

        ```json theme={null}
        {
          "servers": {
            "everflow": {
              "url": "https://mcp.eflow.team",
              "headers": {
                "X-Eflow-API-Key": "your-network-api-key"
              }
            }
          }
        }
        ```

        <Warning>
          `.vscode/mcp.json` holds your network API key in plaintext and often lives inside a repo. Add it to `.gitignore` so the key is never committed.
        </Warning>
      </Step>

      <Step title="Open Copilot Chat in Agent mode">
        The Everflow tools will appear in the tool picker.
      </Step>
    </Steps>
  </Tab>
</Tabs>

***

## Verify the connection

Once connected in any client, run this prompt to confirm everything is working:

> "Call get\_account\_info and tell me my network name, default timezone, and default currency."

A successful response confirms your API key is valid, your network has MCP access enabled, and the MCP server is reachable.

***

## First questions to try

Not sure where to start? Ask in plain language — a few examples:

* "How did my top offers perform last week?"
* "Why was transaction `<id>` rejected?"
* "Which partners have the highest conversion rate but low volume?"
* "Is offer `<id>` pacing toward its cap?"
* "Show revenue by partner for this month."

The server also advertises its capabilities to the assistant on connect, so "what can you help me with?" gives a grounded, Everflow-specific answer.

***

## Debug with MCP Inspector

If a client isn't connecting or tools aren't appearing, the [MCP Inspector](https://github.com/modelcontextprotocol/inspector) lets you test the server directly — independent of any AI client config.

<Steps>
  <Step title="Run the inspector">
    No install required:

    ```bash theme={null}
    npx @modelcontextprotocol/inspector
    ```
  </Step>

  <Step title="Configure the connection in the inspector UI">
    | Field        | Value                    |
    | ------------ | ------------------------ |
    | Transport    | Streamable HTTP          |
    | URL          | `https://mcp.eflow.team` |
    | Header name  | `X-Eflow-API-Key`        |
    | Header value | `your-network-api-key`   |
  </Step>

  <Step title="Connect and call a test tool">
    Click **Connect**, then call `get_account_info` from the Tools tab. A valid response confirms the server is reachable and your key is accepted. If this works but your AI client still can't connect, the issue is in your client config, not the server.
  </Step>
</Steps>

***

## Troubleshooting

| Symptom                                                                         | Likely cause                                                                  | Fix                                                                           |
| ------------------------------------------------------------------------------- | ----------------------------------------------------------------------------- | ----------------------------------------------------------------------------- |
| Connection refused or timeout                                                   | MCP not enabled for your network                                              | Email [support@everflow.io](mailto:support@everflow.io) to request access     |
| `401 Unauthorized`                                                              | Invalid or missing API key                                                    | Verify the key in Control Center → Security                                   |
| `403 Forbidden`                                                                 | Key is not a Network key                                                      | Affiliate and advertiser keys are not accepted                                |
| Tools not appearing in client                                                   | Config file syntax error                                                      | Validate your JSON — trailing commas are invalid                              |
| `not valid MCP server configurations and were skipped` on Claude Desktop launch | Claude Desktop does not accept the `url` + `headers` (Streamable HTTP) format | Use the `mcp-remote` stdio config shown in the **Claude Desktop** tab above   |
| Partial data returned                                                           | Limited affiliate scope on your key                                           | Employees with scoped access only see their assigned affiliates               |
| `npx` fails with "command not found" or hangs                                   | Node.js not installed                                                         | Install Node.js from [nodejs.org](https://nodejs.org/en/download), then retry |

***

## What's next

<CardGroup cols={2}>
  <Card title="Prompt Library" icon="message-lines" href="/ai-automation/mcp/prompts">
    Ready-to-use prompts for reporting, partner health checks, and traffic investigation.
  </Card>

  <Card title="Agentic Examples" icon="wand-magic-sparkles" href="/ai-automation/mcp/examples">
    End-to-end multi-step workflow traces showing exactly what the agent does.
  </Card>
</CardGroup>