Wiro MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WIRO_API_KEY | Yes | Your Wiro project API key | |
| WIRO_API_SECRET | No | Your Wiro project API secret (for signature auth) | |
| WIRO_API_BASE_URL | No | Override API base URL (default: https://api.wiro.ai/v1) | https://api.wiro.ai/v1 |
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 |
|---|---|
| search_modelsA | Search and browse AI models on Wiro. Choose a model from the result and call the returned |
| get_model_schemaA | Get one model’s typed parameters, options, defaults, required fields, and pricing. Catalog fields such as |
| recommend_modelA | Describe a generation goal in natural language and receive ranked model recommendations. Follow the returned |
| exploreA | Browse curated Wiro models grouped by category. Choose a model and call |
| run_modelA | Run any AI model on Wiro. Supports image, video, text, audio, 3D, and more. Call |
| wait_for_taskA | Wait for an existing Wiro task without submitting a new model run. If it is still running, repeat the exact |
| get_taskA | Get the current status and output of one task. By default this is an immediate check. For an active task, follow the returned |
| list_tasksA | List the authenticated project’s recent model-generation tasks. Use this to find work from previous conversations, then call |
| get_task_priceA | Get one task’s final charged cost. Successful tasks are billed; failed tasks are not. If the task is active, follow the returned |
| cancel_taskA | Cancel a task that is still queued, before worker assignment. This changes remote state. Use |
| kill_taskA | Stop a task that is already running. This changes remote state and can discard in-progress work. Use |
| upload_fileA | Upload a remotely accessible file to Wiro. Most models accept source URLs directly, so use this only when the model schema requires a Wiro-hosted file or the same file will be reused. |
| search_docsA | Search official Wiro guides, API references, examples, and how-to documentation. |
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 13 tools
Most tools target distinct resources and actions, but search_models and explore both describe browsing/choosing models, and recommend_model also overlaps in model discovery. The detailed descriptions and explicit nextAction guidance help reduce misselection, so the ambiguity is minor.
The vast majority of tools follow a clear verb_noun snake_case pattern: search_models, get_model_schema, run_model, cancel_task, upload_file. The single bare-verb tool 'explore' breaks the pattern slightly, but the overall naming scheme is predictable and readable.
Thirteen tools is well within the ideal range for a model-execution platform and each tool addresses a distinct phase: discovery, schema inspection, execution, task monitoring, cancellation, pricing, file upload, and documentation. No tool feels unnecessary, and the count is not bloated.
The tool surface covers the full model workflow: find/recommend/explore models, inspect schemas, run models, wait for tasks, retrieve task status, list historical tasks, check pricing, cancel or kill tasks, upload files, and search docs. There are no obvious dead ends or missing lifecycle operations for the domain.