Theta EdgeCloud On-Demand API MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| THETA_API_KEY | Yes | Your Theta EdgeCloud API key | |
| THETA_API_BASE_URL | No | API base URL (default: https://api.thetaedgecloud.com) | https://api.thetaedgecloud.com |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_servicesA | List all available AI models and services on Theta EdgeCloud. Returns service names, descriptions, and input/output specifications. |
| inferB | Run AI inference on a Theta EdgeCloud model. Supports image generation, audio transcription, text generation, and more. IMPORTANT: Call list_services first to see available services and their required inputs. |
| get_request_statusA | Check the status of an inference request. Use this to get results of async requests. |
| get_upload_urlA | Get a presigned URL to upload a file for inference. Use this when you need to upload a local file (audio, image, etc.) before running inference. |
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 4 tools
Each tool has a clearly distinct role: listing services, running inference, checking request status, and obtaining upload URLs. There is no meaningful overlap or ambiguity between them.
Most tools follow a verb_noun pattern (list_services, get_request_status, get_upload_url), but infer is a single verb without an object. This is a minor deviation and the overall naming is still clear and predictable.
Four tools is well-scoped for this server's purpose: service discovery, inference execution, asynchronous status checking, and upload support. Each tool earns its place without unnecessary bloat.
The tool surface covers the full lifecycle of an on-demand inference request: discover services, upload inputs when needed, trigger inference, and poll for results. No obvious gaps exist for the stated domain.