Skip to main content
Glama

Grok MCP

chat_with_reasoning

Solve complex problems step-by-step using reasoning models to provide both final answers and detailed thinking processes for math, logic puzzles, and analytical challenges.

Instructions

Uses Grok's reasoning models to think through complex problems step-by-step. This is perfect for math problems, logic puzzles, or anything requiring careful thinking. You'll get both the final answer AND the reasoning process that led to it. Think of it like showing your work in math class. Only works with reasoning models: grok-4, grok-3-mini, or grok-3-mini-fast. Args: prompt: The problem or question you need solved model: Which reasoning model to use (default is grok-3-mini) system_prompt: Instructions for how the AI should approach the problem reasoning_effort: "low" or "high" (only for grok-3-mini models, not grok-4) temperature: Controls randomness 0-2 (lower = more focused) max_tokens: Maximum length of response top_p: Alternative way to control randomness Returns a dict with 'content' (the answer), 'reasoning_content' (the thinking process), and 'usage' (token counts).

Input Schema

NameRequiredDescriptionDefault
max_tokensNo
modelNogrok-3-mini
promptYes
reasoning_effortNo
system_promptNo
temperatureNo
top_pNo

Input Schema (JSON Schema)

{ "properties": { "max_tokens": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "title": "Max Tokens" }, "model": { "default": "grok-3-mini", "title": "Model", "type": "string" }, "prompt": { "title": "Prompt", "type": "string" }, "reasoning_effort": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "Reasoning Effort" }, "system_prompt": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "System Prompt" }, "temperature": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null, "title": "Temperature" }, "top_p": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null, "title": "Top P" } }, "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