AI API MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MAX_RETRIES | No | Maximum number of retries (default: 3) | 3 |
| RETRY_DELAY | No | Delay between retries in seconds (default: 1.0) | 1.0 |
| GROK_API_KEY | No | Your xAI Grok API key | |
| GROK_BASE_URL | No | Custom base URL for xAI API | |
| GOOGLE_API_KEY | No | Your Google API key | |
| OPENAI_API_KEY | No | Your OpenAI API key | |
| OPENAI_BASE_URL | No | Custom base URL for OpenAI API | |
| ANTHROPIC_API_KEY | No | Your Anthropic API key |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| chatC | Chat with AI models from various providers |
| list_modelsB | List all available AI models from all configured providers Returns: List of model information including ID, name, provider, and capabilities |
| compareC | Compare responses from multiple AI models |
| analyzeC | Analyze content using AI models |
| generateC | Generate content using AI models |
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 5 tools
analyze and generate both use AI models and could be confused with each other or with chat; their boundaries are unclear from names and descriptions, making it hard to predict which tool to use for tasks like summarization versus creation.
Four tools use bare verbs (compare, analyze, chat, generate) while one uses a verb_noun pattern (list_models), creating a mixed convention that is readable but inconsistent.
Five tools is reasonable for an AI API wrapper, covering core operations without excessive bloat, though it leans slightly thin given the breadth of possible AI interactions.
The surface covers listing, chatting, generating, analyzing, and comparing, but lacks key lifecycle operations such as getting provider quota or model details, and there is no explicit create/delete to round out CRUD.