# OceanToken

Connects your coding agent to an index of 500+ AI models for media generation, pricing estimates, and delegated sub-tasks.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: OceanTokenAI
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/OceanTokenAI/oceantoken-plugins
- Updated: 2026-10-21
- HTML: https://affpapa.org/en/nevibecode/mcp/oceantoken

## What it does

This server exposes an endpoint to query external AI models directly from your development workspace. Agents can trigger text-to-image workflows, produce voice narration, transcribe audio clips into SRT or VTT subtitles, and assemble video clips from initial frames.

The tool suite includes `estimate_cost` to inspect request prices against your available funds before running a generation. Secondary routines can be handed off to alternate models via `ask_model`. You need an OceanToken profile with prefunded credits for tool calls to run.

## Requirements
- Remote server: `https://mcp.oceantoken.ai/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mcp https://mcp.oceantoken.ai/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add oceantoken --url https://mcp.oceantoken.ai/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "oceantoken": {
            "url": "https://mcp.oceantoken.ai/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "oceantoken": {
            "type": "http",
            "url": "https://mcp.oceantoken.ai/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http oceantoken https://mcp.oceantoken.ai/mcp
```

## When to use it
- calculate query cost before dispatching an API call
- generate video and image assets inside the project
- transcribe spoken audio into SRT or VTT caption files
- delegate secondary steps to cheaper external models

## Example prompts
- Estimate the price and generate an image for the hero section using OceanToken
- Transcribe interview.mp3 into VTT subtitles
- Hand off this refactoring sub-task to DeepSeek with ask_model

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107701
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26673
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23283
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9369
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9298

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md