# AI/ML API MCP server

> Run chat, image, video and speech models and agent tools from 70+ providers through one hosted connector.

- Listing: https://mcp.tc/i/ai-ml-api
- Connect: use the server's own URL `https://mcp.aimlapi.com/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: AI/ML API
- Homepage: <https://aimlapi.com/>

## About

Connects an assistant to the AI/ML API platform, which offers 500+ AI models for text, image, video, audio and embeddings, plus agentic tools such as web search and social media, SEO and ads data. Usage is billed from one balance.

Runs as a hosted remote server over Streamable HTTP at mcp.aimlapi.com. Clients sign in to AI/ML API in the browser and approve access. The vendor also describes API key setup for some clients. Usage is paid from the account balance.

## What it can do

- Run chat and reasoning models from many providers
- Generate images, video and speech
- Create embeddings
- Search the web
- Pull social media, SEO and ads data

## Example prompts

- "Generate an image of a lighthouse at dusk using an image model."
- "Ask a reasoning model to review this function for race conditions."
- "Create embeddings for these three paragraphs."
- "Search the web for recent news about open-source LLMs."

## Install

### Claude Code

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

```bash
claude mcp add --transport http ai-ml-api https://mcp.aimlapi.com/mcp
```

2. Start Claude Code, type `/mcp`, pick **ai-ml-api** and choose **Authenticate**. A browser window opens for the AI/ML API 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 **AI/ML API** and paste this URL:

```url
https://mcp.aimlapi.com/mcp
```

3. Click **Add**, then **Connect**, and sign in when AI/ML API 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=AI%2FML%20API&connectorUrl=https%3A%2F%2Fmcp.aimlapi.com%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://mcp.aimlapi.com/mcp` and click **Add**.

3. Click **Connect** and sign in when AI/ML API 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://mcp.aimlapi.com/mcp` as the server URL, then for authentication choose **OAuth**. ChatGPT sends you to AI/ML API 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=ai-ml-api&config=eyJ1cmwiOiJodHRwczovL21jcC5haW1sYXBpLmNvbS9tY3AifQ%3D%3D>) (opens Cursor)

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

`mcp.json`:

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

Or from a terminal:

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

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

`.vscode/mcp.json`:

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

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

`config.toml`:

```toml
[mcp_servers.ai-ml-api]
url = "https://mcp.aimlapi.com/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http ai-ml-api https://mcp.aimlapi.com/mcp
```

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

## Details

- Last checked: 2026-11-18 (reachable, asks for credentials)
- Listed: 2026-11-11
- Updated: 2026-11-11

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