Skip to main content
Glama
merterbak

Grok MCP

by merterbak
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

chat

Send a prompt to a Grok model and get its reply, with optional session history, system instructions, model choice, priority processing, and token usage tracking.

Instructions

Send a text prompt to a Grok model and return its reply.

Replays prior turns from `chats/{session}.json` when a session is given,
then appends the new user message and saves the round trip.

Args:
    prompt: User message to send to the model.
    session: Optional session name. Loads and appends history to `chats/{session}.json`.
    model: Grok model id (default `grok-4.6`).
    system_prompt: Optional system instruction prepended to the conversation.
    agent_count: 4 or 16. Only valid with `grok-4.20-multi-agent` for multi-agent research.
    service_tier: `"default"` or `"priority"`. Priority is processed faster at a higher token price.
    show_usage: Append a token usage and cost footer to the reply (default False).

Returns:
    The assistant's reply text, plus a token usage and cost footer when `show_usage` is true.

Input Schema

NameRequiredDescriptionDefault
modelNogrok-4.6
promptYes
sessionNo
show_usageNo
agent_countNo
service_tierNo
system_promptNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.0.4
    • changedInput schema / properties / model / default
      Previous value: -"grok-4.3"New value: +"grok-4.6"
    • addedInput schema / properties / service_tier
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Service Tier"
+}
  2. Changed1 schema field changedv1.0.1
    • addedInput schema / properties / show_usage
      Added value: +{
+  "default": false,
+  "title": "Show Usage",
+  "type": "boolean"
+}
  3. Added
  4. Removed
  5. Added
  6. Removed
  7. Changed1 schema field changed
    • addedInput schema / properties / agent_count
      Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Agent Count"
+}
  8. Added
  9. Removed
  10. Changed1 schema field changed
    • changedInput schema / properties / model / default
      Previous value: -"grok-4"New value: +"grok-4-1-fast-reasoning"
  11. Changed2 schema fields changed
    • addedInput schema / properties / session
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Session"
+}
    • removedInput schema / properties / store_messages
      Removed value: -{
-  "default": false,
-  "title": "Store Messages",
-  "type": "boolean"
-}
  12. Changed11 schema fields changed
    • removedInput schema / properties / frequency_penalty
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "number"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "Frequency Penalty"
-}
    • removedInput schema / properties / max_tokens
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "integer"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "Max Tokens"
-}
    • changedInput schema / properties / model / default
      Previous value: -"grok-4-1-fast-non-reasoning"New value: +"grok-4"
    • removedInput schema / properties / presence_penalty
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "number"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "Presence Penalty"
-}
    • removedInput schema / properties / reasoning_effort
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "Reasoning Effort"
-}
    • removedInput schema / properties / stop
      Removed value: -{
-  "anyOf": [
-    {
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "Stop"
-}
    • addedInput schema / properties / store_messages
      Added value: +{
+  "default": false,
+  "title": "Store Messages",
+  "type": "boolean"
+}
    • removedInput schema / properties / temperature
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "number"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "Temperature"
-}
    • removedInput schema / properties / top_p
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "number"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "Top P"
-}
    • removedInput schema / properties / use_conversation_history
      Removed value: -{
-  "default": false,
-  "title": "Use Conversation History",
-  "type": "boolean"
-}
    • changedOutput schema / (root)
      Previous value: -{
-  "properties": {
-    "result": {
-      "title": "Result",
-      "type": "string"
-    }
-  },
-  "required": [
-    "result"
-  ],
-  "title": "chatOutput",
-  "type": "object"
-}New value: +null
  13. Changed2 schema fields changedv1.0.0
    • changedInput schema / properties / model / default
      Previous value: -"grok-4-fast"New value: +"grok-4-1-fast-non-reasoning"
    • addedInput schema / title
      Added value: +"chatArguments"
  14. First observed

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does well: it discloses that a session causes history to be loaded from and appended to chats/{session}.json, that the new user message and round trip are persisted, and that priority tier costs more. It omits auth requirements, error/rate-limit behavior, and whether a session file is created when absent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded one-line summary followed by compact Args/Returns blocks; every entry carries information. Slightly formulaic and the model default is redundant with the schema, but there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description adequately covers the return value (reply text plus optional usage/cost footer) as well as the stateful side effect on chats/{session}.json. Remaining gaps, such as failure modes and sibling selection, are modest for a 7-param tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description compensates fully by documenting all seven parameters with meaning the schema cannot express: agent_count's allowed values (4 or 16) and model restriction, service_tier semantics, system_prompt prepending behavior, session file path, and show_usage's footer effect.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Send a text prompt to a Grok model and return its reply') and clarifies session replay/append behavior. It does not distinguish itself from close siblings like stateful_chat or grok_agent, so an agent must infer which chat variant to pick.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied through parameter notes rather than stated: it says agent_count is only valid with grok-4.20-multi-agent and explains service_tier's speed/price tradeoff. Nothing says when to choose this over stateful_chat, grok_agent, chat_with_files, or chat_with_vision.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools