Grok MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GROK_API_KEY | Yes | Your API key from x.ai (https://x.ai) |
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 |
|---|---|
| list_modelsB | List all models available for use with the Grok API |
| get_modelC | Get details about a specific model |
| create_chat_completionC | Create a chat completion with the Grok API |
| create_completionC | Create a text completion with the Grok API |
| create_embeddingsC | Create embeddings for text with the Grok 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 5 tools
Each tool has a clearly distinct purpose with no overlap: create_chat_completion and create_completion handle different types of text generation, create_embeddings is for vector representations, get_model retrieves specific model details, and list_models shows all available models. The descriptions reinforce these distinctions, making misselection unlikely.
All tools follow a consistent verb_noun pattern (e.g., create_chat_completion, list_models) using snake_case throughout. The naming is predictable and readable, with no deviations in style or convention across the set.
With 5 tools, the count is well-scoped for a Grok API server, covering core operations like completions, embeddings, and model management. Each tool earns its place without feeling excessive or insufficient for the domain.
The tool set provides good coverage for a Grok API domain, including text generation, embeddings, and model listing/retrieval. A minor gap exists in lacking update or delete operations for models or completions, but agents can work around this for typical workflows.