# WaveSpeed (MCP server)

> WaveSpeed is an MCP server that adds search and knowledge tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Run any model on the live WaveSpeed catalog: image, video, audio, 3D. It has 37 GitHub stars, is released under the MIT license and runs locally with npx -y @wavespeed/mcp.

An MCP server for the WaveSpeed platform: run any model on the live catalog — image, video, audio, 3D — from Claude Code, Claude Desktop, Cursor, Cline, or any MCP client.

## Key facts

| Fact | Value |
|---|---|
| Repository | https://github.com/WaveSpeedAI/mcp-server |
| GitHub stars | 37 |
| License | MIT |
| Language | TypeScript |
| Transport | stdio, streamable-http |
| Packages | npm: @wavespeed/mcp |
| Remote URL | https://api.wavespeed.ai/mcp |
| Needs API key | no |
| Official | yes |
| Works with | Claude Desktop, Claude Code, Cursor, VS Code, Claude.ai, ChatGPT |
| Category | AI & search |
| Latest release | none |
| Last commit | Nov 15, 2026 |
| MCP registry name | ai.wavespeed/mcp |

## Install

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "wavespeed": {
      "command": "npx",
      "args": [
        "-y",
        "@wavespeed/mcp"
      ],
      "env": {
        "WAVESPEED_API_KEY": "your-value"
      }
    }
  }
}
```

Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.

### Claude Code

```sh
claude mcp add --env WAVESPEED_API_KEY=your-value --transport stdio wavespeed -- npx -y @wavespeed/mcp
```

### Cursor (.cursor/mcp.json)

```json
{
  "mcpServers": {
    "wavespeed": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@wavespeed/mcp"
      ],
      "env": {
        "WAVESPEED_API_KEY": "your-value"
      }
    }
  }
}
```

Project file; use ~/.cursor/mcp.json to enable it in every project.

### VS Code (.vscode/mcp.json)

```json
{
  "inputs": [
    {
      "type": "promptString",
      "id": "wavespeed_api_key",
      "description": "WAVESPEED_API_KEY",
      "password": true
    }
  ],
  "servers": {
    "wavespeed": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@wavespeed/mcp"
      ],
      "env": {
        "WAVESPEED_API_KEY": "${input:wavespeed_api_key}"
      }
    }
  }
}
```

### Claude Code (remote)

```sh
claude mcp add --transport http wavespeed "https://api.wavespeed.ai/mcp"
```

The same server is also hosted as a remote MCP endpoint, so nothing runs on your machine.

Config formats checked against the official docs on 2026-10-07.

## Environment variables

- `WAVESPEED_API_KEY` (secret): WaveSpeed API key (https://wavespeed.ai/accesskey). Optional when the wavespeed CLI is logged in.
- `WAVESPEED_BASE_URL`: Override the WaveSpeed API base URL. Defaults to https://api.wavespeed.ai.
- `WAVESPEED_CLIENT_NAME`: Override the client name reported for channel attribution. Defaults to wavespeed-mcp.

## Tools

- `list_models`: Search the live catalog by text or modality type
- `get_model_schema`: A model's real input schema (required, properties, defaults), with a link to the model's playground page
- `run_model`: Submit + wait; rejects input keys the model doesn't accept; @path inputs upload automatically; returns output URLs
- `generate_image`: Image from a prompt with the /chat image models (default Seedream 5.5); reference images use the model's edit endpoint
- `edit_image`: Edit, restyle or combine existing images with the same models
- `generate_video`: Video from a prompt, a first/last frame or reference images/videos/audio, with the /chat video models (default…
- `edit_video`: Edit an existing video, optionally with reference images/audio
- `extend_video`: Continue an existing video with new footage
- `get_price`: Cost estimate for the inputs you pass (no charge), with a link to the model's playground page
- `get_balance`: Account credit balance, with the top-up link
- `list_predictions`: Run history (default last 24h); filter by model, status, time range
- `list_billings`: Itemized charges and refunds (needs a Billing-access key)
- `get_usage`: Spend, request counts and per-model breakdown (default last 7 days; needs a Billing-access key)
- `delete_predictions`: Delete finished runs from the history (up to 100; needs confirm: true, cannot be undone from here)
- `upload_file`: Local file → hosted URL (24h content-hash dedupe)
- `get_prediction`: Status/outputs of any run by id; optional waitseconds to wait for it

## Similar MCP servers

- [OmniSeek](https://appsgit.com/mcp-servers/omniseek): Give your AI agent what web search doesn't reach: podcasts and videos, Chinese communities, papers. (100 stars, Apache-2.0)
- [LibreJustice](https://appsgit.com/mcp-servers/librejustice): Search French-language and European case law and French legal texts (codes, statutes, treaties). (36 stars, Apache-2.0, official)
- [loci](https://appsgit.com/mcp-servers/loci): Cross-session memory and hybrid RAG over your notes and docs. (101 stars, MIT)
- [Parallel Search MCP](https://appsgit.com/mcp-servers/parallel-search-mcp): The best web search for your AI Agent. (33 stars, MIT, official)
- [Agent Search MCP](https://appsgit.com/mcp-servers/agent-search-mcp): Free-first Chinese and English web search MCP using zero-key sources and inspectable evidence. (113 stars, Apache-2.0)
- [Holographic Memory](https://appsgit.com/mcp-servers/holographic-memory): Local persistent memory for AI agents with recall, search, forgetting, and encrypted storage. (28 stars, Apache-2.0, official)

---

Canonical page: https://appsgit.com/mcp-servers/wavespeed
Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed daily.
Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.
