Skip to main content
Glama

Grok MCP

stateful_chat

Maintain ongoing conversations with persistent server-side history for up to 30 days, allowing you to continue discussions across sessions without managing chat history manually.

Instructions

Have ongoing conversations that are saved on xAI's servers for up to 30 days. Unlike regular chat, this maintains conversation history server-side, so you can continue conversations across sessions without managing history yourself. Start a new conversation without a response_id, then use the returned ID to continue it later. Super useful for long-running projects or when you want to pick up where you left off days later. Args: prompt: What you want to say in this turn of the conversation response_id: ID from a previous response to continue that conversation (optional) model: Which Grok model to use (default is grok-4) system_prompt: Instructions for the AI (only used when starting new conversation) include_reasoning: Get a summary of the model's thinking process (default False) temperature: Controls creativity 0-2 max_tokens: Maximum length of response Returns a dict with 'content' (the response), 'response_id' (save this to continue later!), 'status', 'model', 'usage', 'stored_until' (expiration date), and optionally 'reasoning' if you requested it.

Input Schema

NameRequiredDescriptionDefault
include_reasoningNo
max_tokensNo
modelNogrok-4
promptYes
response_idNo
system_promptNo
temperatureNo

Input Schema (JSON Schema)

{ "properties": { "include_reasoning": { "default": false, "title": "Include Reasoning", "type": "boolean" }, "max_tokens": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "title": "Max Tokens" }, "model": { "default": "grok-4", "title": "Model", "type": "string" }, "prompt": { "title": "Prompt", "type": "string" }, "response_id": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "Response Id" }, "system_prompt": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "System Prompt" }, "temperature": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null, "title": "Temperature" } }, "required": [ "prompt" ], "type": "object" }

MCP directory API

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/merterbak/Grok-MCP'

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