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

# Connect with MCP

> Connect InterviewFlowAI to Claude or Codex through the Model Context Protocol.

Connect InterviewFlowAI to an AI assistant through the Model Context Protocol (MCP). You can list AI Interviewers, review Candidate details, summarize interviews, update Candidate notes, and change supported Interviewer settings without switching applications.

<Warning>
  Sign in to MCP with the same email address you use for your InterviewFlowAI account. This connects the authenticated MCP session to the correct Company. If you use email and password, sign up for Auth0 first and verify your email address. Check your spam or junk folder for the verification email.
</Warning>

The InterviewFlowAI MCP server uses this URL:

```text theme={null}
https://api.interviewflowai.com/mcp
```

## Choose your MCP client

<Tabs>
  <Tab title="Claude Code CLI">
    <Steps>
      <Step title="Add the InterviewFlowAI server">
        Run:

        ```bash theme={null}
        claude mcp add-json interviewflowai '{"type":"http","url":"https://api.interviewflowai.com/mcp","oauth":{"clientId":"ACYUUGM2Ia9tbufCbwQSELKlyTvlgxem","callbackPort":8765,"scopes":"mcp:read mcp:write"}}'
        ```
      </Step>

      <Step title="Authenticate">
        Start Claude Code, run `/mcp`, select **interviewflowai**, and choose **Authenticate**.
      </Step>

      <Step title="Confirm the connection">
        Run `/mcp` again and confirm that the server is connected.
      </Step>
    </Steps>
  </Tab>

  <Tab title="Claude Desktop">
    <Steps>
      <Step title="Add a custom connector">
        Open **Customize → Connectors**, click **+**, and select **Add custom connector**. Enter **InterviewFlowAI** as the name and `https://api.interviewflowai.com/mcp` as the server URL.

        <img src="https://mintcdn.com/interviewflowai/gIyVdZQEGbxAEZU3/images/mcp/claude-desktop-add-connector.png?fit=max&auto=format&n=gIyVdZQEGbxAEZU3&q=85&s=9d0a94376f929345b4d638cdb5c36733" alt="Claude Add custom connector form with the InterviewFlowAI name and MCP URL" width="1146" height="982" data-path="images/mcp/claude-desktop-add-connector.png" />
      </Step>

      <Step title="Configure authentication">
        Select **Always required** under **Authentication**. Select **Use your own OAuth client** under **OAuth client**.

        <img src="https://mintcdn.com/interviewflowai/gIyVdZQEGbxAEZU3/images/mcp/claude-desktop-oauth-options.png?fit=max&auto=format&n=gIyVdZQEGbxAEZU3&q=85&s=f5a695bc210c9e4e109bd015656594b3" alt="Claude connector authentication settings with Always required and Use your own OAuth client selected" width="1116" height="1444" data-path="images/mcp/claude-desktop-oauth-options.png" />
      </Step>

      <Step title="Enter the OAuth client ID">
        Enter `ACYUUGM2Ia9tbufCbwQSELKlyTvlgxem` as the Client ID. Leave **OAuth Client Secret** blank, then click **Add**.

        <img src="https://mintcdn.com/interviewflowai/gIyVdZQEGbxAEZU3/images/mcp/claude-desktop-client-id.png?fit=max&auto=format&n=gIyVdZQEGbxAEZU3&q=85&s=12726b0f0cf6c29b369cd4c32f0eb5cc" alt="Claude connector form showing the InterviewFlowAI OAuth Client ID and an empty client secret" width="1048" height="1024" data-path="images/mcp/claude-desktop-client-id.png" />
      </Step>

      <Step title="Authenticate">
        Select **Connect** or **Authenticate** for InterviewFlowAI and complete the Auth0 login. Enable InterviewFlowAI from the **Connectors** menu in your conversation.
      </Step>
    </Steps>
  </Tab>

  <Tab title="Codex CLI">
    <Steps>
      <Step title="Configure the MCP server">
        Open the Codex configuration file for your operating system:

        * **macOS and Linux:** `~/.codex/config.toml`
        * **Windows PowerShell:** `$HOME\.codex\config.toml`
        * **Windows Command Prompt:** `%USERPROFILE%\.codex\config.toml`

        Add:

        ```toml theme={null}
        [mcp_servers.interviewflowai]
        url = "https://api.interviewflowai.com/mcp"
        scopes = ["mcp:read", "mcp:write"]

        [mcp_servers.interviewflowai.oauth]
        client_id = "ACYUUGM2Ia9tbufCbwQSELKlyTvlgxem"
        callback_port = 52000
        callback_url = "http://127.0.0.1:52000/callback"
        ```
      </Step>

      <Step title="Authenticate">
        Run `codex mcp login interviewflowai`, then complete the Auth0 login in your browser.
      </Step>

      <Step title="Verify and restart">
        Run `codex mcp get interviewflowai`. Confirm that the server is enabled, then restart Codex.
      </Step>
    </Steps>
  </Tab>

  <Tab title="Codex Desktop">
    <Steps>
      <Step title="Configure the shared MCP server">
        Quit Codex Desktop and add the Codex CLI configuration shown above to the configuration file for your operating system:

        * **macOS and Linux:** `~/.codex/config.toml`
        * **Windows PowerShell:** `$HOME\.codex\config.toml`
        * **Windows Command Prompt:** `%USERPROFILE%\.codex\config.toml`
      </Step>

      <Step title="Authenticate">
        Open Codex Desktop and go to **Settings → MCP Servers**. Select **Authenticate** for **interviewflowai** and complete the Auth0 login.
      </Step>

      <Step title="Restart and verify">
        Restart Codex Desktop. Type `/mcp` in the composer and confirm that InterviewFlowAI is connected.
      </Step>
    </Steps>
  </Tab>
</Tabs>

## Permissions

The `mcp:read` scope lets your assistant list and inspect AI Interviewers and Candidates. The `mcp:write` scope lets an **Owner** update Candidate notes, custom fields, visibility, and archived status. InterviewFlowAI does not expose write tools to **Viewers**.

Confirm every write action before you allow your assistant to make a change.

## Try the connection

Ask your assistant:

* “Show me the Candidates who completed the interview.”
* “Show me the top 10 Candidates by interview score.”
* “Show me the Candidates with an interview score of 70 or above.”