Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@geez Explain quantum entanglement in simple terms"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Phone-first MCP tool that lets Claude (or any MCP client) call Grok.
Minimal. Requests-only. Zero bloat. Built to run cleanly in Termux / proot-distro.
Because sometimes you just want Claude to be able to ask Grok without dragging the entire Super guard stack along.
Related MCP server: Grok MCP Server
pip install -e .
export XAI_API_KEY=your_xai_key_here # get one at https://console.x.ai
geezThen connect any MCP client (Claude Desktop, Cursor, etc.) to the geez stdio server.
call_grok(
prompt="Explain quantum spin processors in plain English",
system="You are Grok, built by xAI. Be direct and helpful.",
model="grok-3",
max_tokens=800
)Tool | Description |
| Send a prompt to Grok and get the response back |
XAI_API_KEY=... # required
# GROK_API_KEY=... # alias also acceptedSingle dependency beyond stdlib: requests + mcp
No guard pipelines, no Cisco, no Duo, no Stripe — just the call
Phone-native: works in Termux with almost no setup
Fully public and auditable
Made for the same phone-first workflow as the rest of the portfolio.
Call Grok (xAI) from Claude or any MCP client.
Phone-first: uses only requests. Set XAI_API_KEY (or GROK_API_KEY) in the environment before starting the server.
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | grok-3 | |
| prompt | Yes | ||
| system | No | ||
| max_tokens | No | ||
| temperature | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose behavior. It says 'uses only requests' implying a read operation, but does not clarify if it's destructive, auth requirements beyond env vars, rate limits, or side effects. Lacks necessary context for an agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is two sentences, front-loaded with purpose. Concise but missing essential details. For conciseness alone, it is well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having 5 parameters and no annotations, the description only mentions environment setup. It does not cover return values (output schema exists but unmentioned), parameter details, or behavioral context. Severely incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 0% parameter description coverage, and the description adds no meaning to any parameter. It does not explain 'model', 'prompt', 'system', 'max_tokens', or 'temperature', leaving agents uninformed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool calls Grok (xAI) from an MCP client. The verb 'call' and resource 'Grok' are specific. No siblings exist, so differentiation is not needed.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives. Only mentions environment setup as a prerequisite, but no usage context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0call_grokScored across 1 tool
Only one tool exists, so no ambiguity between tools.
Single tool follows a clear verb_noun pattern; no inconsistency.
One tool is borderline thin for an API wrapper; typically 3-15 tools are expected.
The server lacks parameters like model selection or streaming, limiting its capability for complex interactions.
Human-input bridge for AI agents with voice-first answer links, MCP tools, and HTTP APIs.
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
Give AI agents real phone numbers, messages, and voice calls via MCP.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
