# Kinovi MCP server

> Discover AI video, image and audio models, estimate costs, submit generation tasks and poll their status through Kinovi.

- Listing: https://mcp.tc/i/kinovi
- Connect: use the server's own URL `https://kinovi.ai/api/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: [AI & Machine Learning](https://mcp.tc/c/ai-ml)
- Vendor: Kinovi
- Homepage: <https://kinovi.ai/>

## About

Kinovi is a hosted API for running video, image and audio generation models from several providers. The MCP server lets an assistant browse available models, estimate costs, submit generation tasks and poll for results.

It runs as a remote Streamable HTTP endpoint at https://kinovi.ai/api/mcp. The endpoint accepts OAuth tokens with mcp:read and mcp:write scopes. Access needs Kinovi credentials.

## What it can do

- Discover available video, image and audio models
- Estimate the cost of a generation task
- Submit generation tasks
- Poll task status and retrieve results

## Tools (8)

- `list_models`: List public Kinovi image/video/audio generation models that can be submitted right now. (read-only)
- `get_model_params`: Return the parameter contract for one public model: a JSON Schema (when the source schema is convertible), field defaults/options, and media slot limits. (read-only)
- `estimate_cost`: Return the credit cost for one task without creating an order or charging credits. (read-only)
- `create_task`: Submit one generation task.
- `get_task`: Read one task. (read-only)
- `get_account`: Return the authenticated user's email, name, and current credit balance. (read-only)
- `search_docs`: Search the public Kinovi docs for concepts, parameter names, error codes, upload rules, and API/MCP usage. (read-only)
- `create_upload_url`: Use an existing public URL, or get a presigned R2 PUT URL for one image/video/audio file.

## Example prompts

- "List the video models available on Kinovi."
- "Estimate the cost of a 10 second 720p Seedance 2.0 video."
- "Submit a text-to-video task with this prompt and check its status."
- "Poll my last Kinovi task and give me the result link."

## Install

### Claude Code

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

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

2. Start Claude Code, type `/mcp`, pick **kinovi** and choose **Authenticate**. A browser window opens for the Kinovi 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 **Kinovi** and paste this URL:

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

3. Click **Add**, then **Connect**, and sign in when Kinovi 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=Kinovi&connectorUrl=https%3A%2F%2Fkinovi.ai%2Fapi%2Fmcp>) (opens connector settings)

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

3. Click **Connect** and sign in when Kinovi 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://kinovi.ai/api/mcp` as the server URL, then for authentication choose **OAuth**. ChatGPT sends you to Kinovi 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=kinovi&config=eyJ1cmwiOiJodHRwczovL2tpbm92aS5haS9hcGkvbWNwIn0%3D>) (opens Cursor)

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

`mcp.json`:

```json
{
  "mcpServers": {
    "kinovi": {
      "url": "https://kinovi.ai/api/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=kinovi&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fkinovi.ai%2Fapi%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

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

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

`.vscode/mcp.json`:

```json
{
  "servers": {
    "kinovi": {
      "type": "http",
      "url": "https://kinovi.ai/api/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": {
    "kinovi": {
      "serverUrl": "https://kinovi.ai/api/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 kinovi --url https://kinovi.ai/api/mcp
codex mcp login kinovi
```

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

`config.toml`:

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

### Gemini CLI

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

Then, inside Gemini CLI, run `/mcp auth kinovi` 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": {
    "kinovi": {
      "type": "http",
      "url": "https://kinovi.ai/api/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://kinovi.ai/api/mcp`.

## Recent changes

- 2026-11-16 00:21 UTC: Tracking started: 8 tools read. Source: automatic check.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/kinovi#history (Atom feed: https://mcp.tc/i/kinovi/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review.

## Details

- Server version: 1.0.0
- MCP protocol version: 2025-11-25
- Last checked: 2026-11-18 (reachable, asks for credentials)
- Listed: 2026-11-07
- Updated: 2026-11-16

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