Schema | askgrokmcp

askgrokmcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`XAI_API_KEY`	Yes	Your xAI API key
`LOG_REQUESTS`	No	Logs tool/xAI request metadata to stderr	false
`GROK_CHAT_MODEL`	No	Default model for ask_grok, grok_consensus, and grok_validate	grok-4.3
`XAI_MAX_RETRIES`	No	Number of retries for transient errors	2
`GROK_IMAGE_MODEL`	No	Default model for generate_image	grok-imagine-image-quality
`SAFE_WRITE_BASE_DIR`	No	Base directory for image writes	process.cwd()
`LOG_REQUEST_PAYLOADS`	No	Includes full request payloads in logs (use carefully)	false
`XAI_REQUEST_TIMEOUT_MS`	No	Timeout per xAI API request in milliseconds	30000
`XAI_RETRY_BASE_DELAY_MS`	No	Base delay for exponential retry backoff	500

Features and capabilities supported by this server

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
ask_grokB	Ask Grok a question and get a response. Default model: grok-4.3. Supports system prompts and sampling parameters (temperature, max_tokens, top_p). Run list_models to see all available model options.
generate_imageB	Generate an image using Grok's Aurora image model and save it to a local file. Default model: grok-imagine-image-quality. Use the optional 'model' parameter to use a different image model.
list_modelsA	List all xAI models available to your account, including their IDs and capabilities. Use this to discover which models you can pass to ask_grok or generate_image. You can also filter by type: 'chat' for language models or 'image' for image generation.
grok_consensusA	Runs a full iterative Consensus Validation Protocol (CVP) between Claude and Grok. Returns a structured final summary. Default 3-5 rounds. Supports custom round count via the 'rounds' argument.
grok_validateA	Runs a rigorous Validation Protocol on any artifact (code, plan, research, prompt, PR, architecture, etc.). Produces a scored scorecard, identifies weaknesses, and returns an improved version. Use this as your mandatory quality gate before shipping complex work. Default model: grok-4.3.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/entropyvortex/askgrokmcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server