# Frank MCP server

> Run AI-moderated customer interviews and pull research themes with verbatim evidence into your AI assistant.

- Listing: https://mcp.tc/i/frank
- Connect: use the server's own URL `https://api.hifrank.ai/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [Data & Analytics](https://mcp.tc/c/analytics)
- Vendor: Prelaunch.com
- Homepage: <https://hifrank.ai/>

## About

Frank is an AI customer researcher from Prelaunch.com that runs voice and chat interviews with customers and summarizes the results. The MCP server connects an assistant to that research, so you can query interview insights, themes and supporting quotes, and work with research and product data without leaving the chat.

The server is hosted at https://api.hifrank.ai/mcp over streamable HTTP. Access needs a Frank account and credentials from the vendor. The published scopes cover reading and writing research, interviews and products, publishing research and embeds.

## What it can do

- Read customer research and interview data
- Surface themes with verbatim customer quotes
- Read and update product records
- Create and publish research studies

## Example prompts

- "What are the top reasons customers gave for churning in recent Frank interviews?"
- "Summarize themes from last night's interviews with supporting quotes."
- "Create a new research study about onboarding friction for my product."
- "Which feature requests came up most in discovery interviews?"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http frank https://api.hifrank.ai/mcp
```

2. Start Claude Code, type `/mcp`, pick **frank** and choose **Authenticate**. A browser window opens for the Prelaunch.com sign-in.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **Frank** and paste this URL:

```url
https://api.hifrank.ai/mcp
```

3. Click **Add**, then **Connect**, and sign in when Prelaunch.com asks.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Frank&connectorUrl=https%3A%2F%2Fapi.hifrank.ai%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://api.hifrank.ai/mcp` and click **Add**.

3. Click **Connect** and sign in when Prelaunch.com asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**.

2. Enter a name for the server.

3. Under **Connection**, paste `https://api.hifrank.ai/mcp` as the server URL, then for authentication choose **OAuth**. ChatGPT sends you to Prelaunch.com to sign in.

4. Check **I understand and want to continue**, then select **Create as a plugin**.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=frank&config=eyJ1cmwiOiJodHRwczovL2FwaS5oaWZyYW5rLmFpL21jcCJ9>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "frank": {
      "url": "https://api.hifrank.ai/mcp"
    }
  }
}
```

Cursor shows **Needs authentication** next to the server. Click the button beside it to sign in.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=frank&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fapi.hifrank.ai%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"frank","type":"http","url":"https://api.hifrank.ai/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "frank": {
      "type": "http",
      "url": "https://api.hifrank.ai/mcp"
    }
  }
}
```

VS Code asks you to sign in the first time the server starts.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "frank": {
      "serverUrl": "https://api.hifrank.ai/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add frank --url https://api.hifrank.ai/mcp
codex mcp login frank
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.frank]
url = "https://api.hifrank.ai/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http frank https://api.hifrank.ai/mcp
```

Then, inside Gemini CLI, run `/mcp auth frank` to sign in.

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "frank": {
      "type": "http",
      "url": "https://api.hifrank.ai/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://api.hifrank.ai/mcp`.

## Details

- Last checked: 2026-11-14 (reachable, asks for credentials)
- Listed: 2026-11-04
- Updated: 2026-11-04

---
Source: https://mcp.tc/i/frank (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report