Skip to main content
Glama
deenesjakoruzh
PKWadsy

grok-mcp

by PKWadsy
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
JavaScript
Remote

grok-mcp

MCP server that wraps the xAI Grok API. Lets Claude and other AI agents delegate thinking, planning, and real-time search to Grok.

Quick Start

One-liner to add to Claude Code on any device:

claude mcp add grok -e XAI_API_KEY=your-key -- npx -y @pkwadsy/grok-mcp

You need an xAI API key from console.x.ai.

Alternative: project config

Add to your project's .mcp.json:

{
  "mcpServers": {
    "grok": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@pkwadsy/grok-mcp"],
      "env": {
        "XAI_API_KEY": "your-xai-api-key"
      }
    }
  }
}

Related MCP server: grok-search-mcp

Tools

ask_grok

Ask Grok a question with optional file context, web search, and X/Twitter search.

Parameter

Type

Required

Description

prompt

string

yes

The question or task for Grok

files

string[]

no

Files to include in context (see file syntax below)

max_files

number

no

Override max file count (default 50)

max_file_size

number

no

Override max per-file size in KB (default 32)

system_prompt

string

no

Custom system prompt

model

string

no

Model to use (default: grok-4.20-multi-agent)

web_search

boolean

no

Web search, enabled by default

x_search

boolean

no

Enable X/Twitter search

check_files

Dry-run file resolution. Validates all files and shows sizes without calling Grok. If check_files passes, ask_grok will too.

Parameter

Type

Required

Description

files

string[]

yes

Files to check (same syntax as ask_grok)

max_files

number

no

Override max file count (default 50)

max_file_size

number

no

Override max per-file size in KB (default 32)

File syntax

Files are passed as an array of strings with compact syntax:

Syntax

Description

"src/index.ts"

Whole file

"src/index.ts:10-30"

Lines 10 to 30

"src/index.ts:10"

Just line 10

"src/**/*.ts"

Glob pattern

"large-file.ts:force"

Bypass per-file size limit

"large-file.ts:1-100:force"

Combine line range with force

Safety limits

Limit

Default

Override

Files per call

50

max_files param

Per-file size

32 KB

max_file_size param or :force suffix

Total context

256 KB

Hard cap, not overridable

Available models

  • grok-4.20-multi-agent — multi-agent mode, great for architecture and planning (default)

  • grok-4.20-reasoning — flagship reasoning

  • grok-4.20-non-reasoning — fast, no reasoning

  • grok-4.1-fast-reasoning — cheaper reasoning

  • grok-4.1-fast-non-reasoning — cheapest, fast

Examples

Ask with file context:

prompt: "Review this code for bugs"
files: ["src/index.ts", "src/utils.ts:20-50"]

Search the web:

prompt: "What happened in tech news today?"

Search X/Twitter:

prompt: "What are people saying about the new React release?"
x_search: true

Check files before asking:

files: ["src/**/*.ts"]

License

MIT

Available Tools

2 tools
ask_grokA

Ask Grok a question. Grok is great for thinking, planning, architecture, and real-time search via web and X/Twitter. Use web_search for current information from the internet. Use x_search to find and analyze posts on X/Twitter. IMPORTANT: Grok has no context about your conversation or codebase. Always include all relevant context directly in the prompt — file contents, error messages, architecture details, constraints, and goals. The more context you provide, the better Grok's response will be. Do not assume Grok knows anything about the current project. Use the files parameter to automatically include file contents with line numbers — this is preferred over pasting code into the prompt. File paths are resolved relative to the server working directory: /app. Responses include a response_id — pass it back as previous_response_id to continue a conversation without resending context.

ParametersJSON Schema
NameRequiredDescriptionDefault
promptYesThe question or task for Grok. Include all relevant context — constraints, background, and goals — since Grok has no access to your conversation or files. Use the files parameter to attach source code rather than pasting it inline
previous_response_idNoResponse ID from a previous ask_grok call. Continues the conversation — Grok remembers all prior context so you don't need to resend files or repeat background. Not supported by multi-agent model (beta limitation)
filesNoFiles to include in context. Compact syntax: "path/to/file" (whole file), "path/to/file:10-30" (lines 10-30), "path/to/file:10" (just line 10), "src/**/*.ts" (glob pattern), "large-file.ts:force" (bypass per-file size limit). Paths resolve relative to server cwd.
max_filesNoOverride max file count (default 50). Useful when a glob legitimately matches many files
max_file_sizeNoOverride max per-file size in KB (default 32). Applies to all files without :force suffix
system_promptNoCustom system prompt to guide Grok's behavior
modelNoModel to use. Defaults to grok-4.20-multi-agent. Options: grok-4.20-multi-agent, grok-4.20-reasoning, grok-4.20-non-reasoning, grok-4.1-fast-reasoning, grok-4.1-fast-non-reasoning
web_searchNoWeb search is enabled by default. Set to false to disable
x_searchNoEnable X/Twitter search to find and analyze posts

TDQS

A4.9/5.0
Behavior5/5

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

Despite no annotations, the description fully discloses behavioral traits: Grok has no context about conversation or codebase, responses include a response_id for continuation, file inclusion syntax, model options, and search defaults. The limitation of previous_response_id in multi-agent mode is also noted.

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?

The description is fairly long but well-organized, using bold for emphasis and clear sections. Every sentence contributes essential information. Could be slightly more concise, but overall efficient for the complexity covered.

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

Completeness5/5

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

For a tool with 9 parameters and no output schema, the description is comprehensive: covers all input aspects, explains the output (response_id), gives continuation guidance, and addresses the critical context limitation. Complete and actionable.

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 coverage is 100%, but the description adds substantial value: explains the rationale for using files, provides detailed file path syntax, clarifies the purpose of previous_response_id, and describes model options and search behavior. It enriches the parameter meanings significantly beyond the schema.

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

Purpose5/5

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

The description clearly states 'Ask Grok a question' and outlines what Grok excels at (thinking, planning, architecture, real-time search). It distinguishes from related tools like web_search and x_search, though they are not listed as siblings on this server. The purpose is specific and unambiguous.

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

Usage Guidelines5/5

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

Explicitly provides when to use this tool vs alternatives: 'Use web_search for current information... Use x_search to find and analyze posts.' Also gives critical usage guidance: include full context, use files parameter, how to continue conversations with previous_response_id. No ambiguity.

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

check_filesA

Dry-run file resolution. Use this before ask_grok to verify files will resolve correctly and check context size. Uses the same validation as ask_grok — if check_files passes, ask_grok will too. File paths resolve relative to: /app

ParametersJSON Schema
NameRequiredDescriptionDefault
filesYesFiles to check. Same syntax as ask_grok: "path/to/file", "path/to/file:10-30", "src/**/*.ts", "large-file.ts:force"
max_filesNoOverride max file count (default 50)
max_file_sizeNoOverride max per-file size in KB (default 32)

TDQS

A4.4/5.0
Behavior4/5

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

No annotations are provided, so the description carries full burden. It discloses the tool is a dry-run (non-destructive), verifies file resolution, checks context size, and states that file paths resolve relative to /app. It doesn't detail error behavior or rate limits, but for a simple check tool this is adequate.

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

Conciseness5/5

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

The description is extremely concise at three sentences, with the primary purpose front-loaded. Every sentence adds essential information without redundancy.

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?

Given the tool's simplicity, no output schema, and a single sibling, the description covers the core functionality and relationship well. It explains validation equivalence and file resolution. It does not describe the return format, but the overall completeness is sufficient for an agent to use the tool correctly.

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

Parameters3/5

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

The input schema has 100% coverage with detailed descriptions for all three parameters. The description adds an important context note about file paths resolving relative to /app, which is not in the schema. However, this is environmental context rather than parameter semantics, so the baseline 3 is appropriate.

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

Purpose5/5

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

The description clearly states the tool performs a 'dry-run file resolution' and explicitly differentiates it from its sibling 'ask_grok' by positioning it as a preparatory verification step. The verb 'check' and noun 'files' are specific.

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

Usage Guidelines5/5

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

The description provides explicit usage guidance: 'Use this before ask_grok' and explains that if check_files passes, ask_grok will too. It also notes the same validation logic, giving clear context for when to use this tool versus the alternative.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv1.4.0
    • First observedask_grok
    • First observedcheck_files
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.4/5.0

Scored across 2 tools

Disambiguation5/5

ask_grok and check_files serve clearly distinct purposes: one is for querying Grok, the other is a dry-run validator for file resolution. No overlap or ambiguity.

Naming Consistency5/5

Both tool names follow a consistent verb_noun pattern (ask_grok, check_files), using underscores and clear verbs.

Tool Count3/5

Only 2 tools feels thin for a server that provides access to Grok, which could benefit from additional tools for conversation management or specialized searches.

Completeness2/5

The tool set lacks basic conversational features like retrieving history or managing context, and the promised web_search/x_search capabilities are not exposed as separate tools, limiting functionality.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers