WaveSpeed MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WAVESPEED_API_KEY | Yes | WaveSpeed API key from https://wavespeed.ai/accesskey. Optional if the WaveSpeed CLI is already logged in. | |
| WAVESPEED_BASE_URL | No | Override the WaveSpeed API base URL. | https://api.wavespeed.ai |
| WAVESPEED_CLIENT_NAME | No | Client name reported for usage attribution. | wavespeed-mcp |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_modelsA | 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. |
| get_model_schemaA | Get a model's real input schema (required fields, properties, defaults). Call this before run_model so inputs match what the model actually accepts. |
| run_modelA | 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. |
| get_priceA | 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. |
| get_balanceA | Show the WaveSpeed account credit balance. |
| upload_fileA | 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. |
| get_predictionA | Fetch the status and outputs of a past or in-flight prediction by id — use to recover a run that hit the wait limit. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool has a clear purpose: model discovery, schema, execution, pricing, balance, upload, and status. There is slight overlap between run_model and upload_file since run_model can handle uploads, but descriptions clarify when upload_file is needed.
All tool names follow a consistent verb_noun pattern with clear verbs (list, get, run, get, get, upload, get). No mixed conventions or vague naming.
With 7 tools, the server covers the essential workflow for model execution and account management without unnecessary bloat. Each tool serves a distinct need in the lifecycle.
The tool set covers model discovery, schema retrieval, execution, pricing, balance, file upload, and result retrieval. A minor gap is the absence of a cancel/delete prediction tool, but the core workflow is well covered.