# ai.wavespeed/mcp (npm · @wavespeed/mcp)

Run any model on the live WaveSpeed catalog: image, video, audio, 3D.

- Trust score: 93/100 (high trust)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- npm · `@wavespeed/mcp`: 93/100 (this document), [markdown](https://verifymcp.io/servers/ai-wavespeed-mcp/wavespeed-mcp.md), [page](https://verifymcp.io/servers/ai-wavespeed-mcp/wavespeed-mcp)

## Channel facts

- Registry: `npm`
- Package: `@wavespeed/mcp`
- Version: `1.0.7`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 97 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to WaveSpeedAI/mcp-server).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 25 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 81/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 575 tokens (~82/item across 7 items; 7 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 83/100
  - Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the ai.wavespeed/mcp server?

ai.wavespeed/mcp runs locally as an npm package, launched with npx -y @wavespeed/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add ai-wavespeed-mcp -- npx -y @wavespeed/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "ai-wavespeed-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@wavespeed/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-wavespeed-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@wavespeed/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ai-wavespeed-mcp -- npx -y @wavespeed/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-wavespeed-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@wavespeed/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-wavespeed-mcp --command npx --arg -y --arg @wavespeed/mcp
```

### Hermes

```yaml
mcp_servers:
  ai-wavespeed-mcp:
    command: "npx"
    args: ["-y", "@wavespeed/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "ai-wavespeed-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@wavespeed/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-wavespeed-mcp -t stdio -c npx -a -y @wavespeed/mcp
```

### Other

```json
{
  "mcpServers": {
    "ai-wavespeed-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@wavespeed/mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 93, −2)

- [functional] Stability: pass → 0.83

### 2026-09-18 (score 95, 0)

- [security] Stability: 0.97 → pass

### 2026-09-17 (score 95, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 94, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 93, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 92, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-08 (score 91, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-06 (score 90, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (7)

### `list_models` (~109 tokens)

Search the live WaveSpeed model catalog (image, video, audio, 3D). Returns model IDs usable with run_model. Do not invent model IDs — always pick one returned by this tool.

Input parameters:

- `limit` (integer): Max results
- `query` (string): Free-text filter on id/name/description
- `refresh` (boolean): Bypass the 1h catalog cache
- `type` (string): Filter by modality type, e.g. text-to-image, image-to-video

### `get_model_schema` (~65 tokens)

Get a model's real input schema (required fields, properties, defaults). Call this before run_model so inputs match what the model actually accepts.

Input parameters:

- `model` (string, required): Model ID from list_models, e.g. bytedance/seedream-v5.0-pro

### `run_model` (~134 tokens)

Run any WaveSpeed model. input keys come from get_model_schema. Local files: pass "@./path" string values — they are uploaded and replaced with hosted URLs (bare paths are NOT uploaded). Returns output URLs. If the wait limit is hit, the task keeps running; recover it with get_prediction.

Input parameters:

- `input` (object, required): Model inputs per its schema (e.g. {"prompt": "...", "aspect_ratio": "16:9"})
- `model` (string, required): Model ID from list_models
- `wait_seconds` (integer): Max seconds to wait; 0 = submit only and return the prediction id

### `get_price` (~67 tokens)

Estimate the cost of a run before executing it (no charge). Provide the same input you would pass to run_model — pricing often depends on inputs like duration or resolution.

Input parameters:

- `input` (object): Inputs the quote should account for
- `model` (string, required): Model ID from list_models

### `get_balance` (~16 tokens)

Show the WaveSpeed account credit balance.

### `upload_file` (~56 tokens)

Upload a local file to WaveSpeed and get its hosted URL (identical bytes reuse the same upload for 24h). Usually unnecessary — run_model handles "@./path" inputs itself.

Input parameters:

- `path` (string, required): Local file path

### `get_prediction` (~47 tokens)

Fetch the status and outputs of a past or in-flight prediction by id — use to recover a run that hit the wait limit.

Input parameters:

- `id` (string, required): Prediction id returned by run_model

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/ai-wavespeed-mcp/wavespeed-mcp#diagnostics

## Score history

- 2026-09-20: 93
- 2026-09-19: 95
- 2026-09-18: 95
- 2026-09-17: 95
- 2026-09-16: 94
- 2026-09-15: 94
- 2026-09-14: 94
- 2026-09-13: 93
- 2026-09-12: 93
- 2026-09-11: 92
- 2026-09-10: 92
- 2026-09-09: 91
- 2026-09-08: 91
- 2026-09-07: 90
- 2026-09-06: 90
- 2026-09-05: 89
- 2026-09-04: 89
- 2026-09-03: 88
- 2026-09-02: 88
- 2026-09-01: 87
- 2026-08-31: 87
- 2026-08-30: 87
- 2026-08-29: 86
- 2026-08-28: 86
- 2026-08-27: 85
- 2026-08-26: 85
- 2026-08-25: 83
- 2026-08-24: 83
- 2026-08-23: 82
- 2026-08-22: 82

## Common questions

### What is the ai.wavespeed/mcp server?

ai.wavespeed/mcp is listed in the public MCP registry as ai.wavespeed/mcp. Run any model on the live WaveSpeed catalog: image, video, audio, 3D. This page covers its npm package (@wavespeed/mcp).

### Is the ai.wavespeed/mcp server safe to use?

ai.wavespeed/mcp scores 93 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the ai.wavespeed/mcp server expose?

ai.wavespeed/mcp exposes 7 tools: list_models, get_model_schema, run_model, get_price, get_balance, and 2 more. Their descriptions and schemas cost roughly 494 tokens of context every time the server is loaded.

### Is the ai.wavespeed/mcp server still maintained?

ai.wavespeed/mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the ai.wavespeed/mcp server under?

ai.wavespeed/mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@wavespeed/mcp
- Socket report: https://socket.dev/npm/package/@wavespeed/mcp
- Repository: https://github.com/WaveSpeedAI/mcp-server
- Website: https://wavespeed.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-wavespeed-mcp/wavespeed-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-wavespeed-mcp/wavespeed-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-wavespeed-mcp/wavespeed-mcp