MCP DeepInfra AI Tools Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ENABLED_TOOLS | No | Comma-separated list of tools to enable. Use "all" to enable all tools | all |
| MODEL_FILL_MASK | No | Default model for fill mask | microsoft/DialoGPT-medium |
| MODEL_EMBEDDINGS | No | Default model for embeddings | sentence-transformers/all-MiniLM-L6-v2 |
| DEEPINFRA_API_KEY | Yes | Your DeepInfra API key | |
| MODEL_GENERATE_IMAGE | No | Default model for image generation | Bria/Bria-3.2 |
| MODEL_TEXT_GENERATION | No | Default model for text generation | meta-llama/Llama-2-7b-chat-hf |
| MODEL_OBJECT_DETECTION | No | Default model for object detection | openai/gpt-4o-mini |
| MODEL_SPEECH_RECOGNITION | No | Default model for speech recognition | openai/whisper-large-v3 |
| MODEL_TEXT_CLASSIFICATION | No | Default model for text classification | microsoft/DialoGPT-medium |
| MODEL_IMAGE_CLASSIFICATION | No | Default model for image classification | openai/gpt-4o-mini |
| MODEL_TOKEN_CLASSIFICATION | No | Default model for token classification | microsoft/DialoGPT-medium |
| MODEL_ZERO_SHOT_IMAGE_CLASSIFICATION | No | Default model for zero-shot image classification | openai/gpt-4o-mini |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageB | Generate an image from a text prompt using DeepInfra OpenAI-compatible API. |
| text_generationB | Generate text completion using DeepInfra OpenAI-compatible API. |
| embeddingsB | Generate embeddings for a list of texts using DeepInfra OpenAI-compatible API. |
| speech_recognitionB | Transcribe audio to text using DeepInfra OpenAI-compatible API (Whisper). |
| zero_shot_image_classificationB | Classify an image with zero-shot labels using DeepInfra OpenAI-compatible API (CLIP). |
| object_detectionB | Detect objects in an image using DeepInfra OpenAI-compatible API with multimodal model. |
| image_classificationC | Classify an image using DeepInfra OpenAI-compatible API with multimodal model. |
| text_classificationB | Classify text using DeepInfra OpenAI-compatible API. |
| token_classificationB | Perform token classification (NER) using DeepInfra OpenAI-compatible API. |
| fill_maskC | Fill masked tokens in text using DeepInfra OpenAI-compatible API. |
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 10 tools
Each tool has a clearly distinct purpose targeting different AI tasks (embeddings, text generation, image generation, classification, etc.). No ambiguity exists as tools are specialized for specific operations like speech recognition vs. text classification, with clear boundaries between them.
All tool names follow a consistent snake_case pattern with descriptive verb_noun or noun_verb structures (e.g., generate_image, text_classification). The naming is uniform across all tools, making them easily predictable and readable.
With 10 tools, the count is well-scoped for an AI tools server covering diverse tasks like text, image, and audio processing. Each tool earns its place by addressing a specific AI function without redundancy or bloat.
The tool set provides comprehensive coverage for common AI tasks (text, image, audio) with clear operations like generation, classification, and detection. Minor gaps might include more advanced or niche AI functions, but core workflows are well-covered for the domain.