- ✓Actively maintained (<30d)
- ✓Documented (README)
- !No standard license detected
- !No description
git clone https://github.com/alexclmy/groki-mcp && cp groki-mcp/*.md ~/.claude/agents/Subagents overview
# Groki MCP Give AI agents a meme factory, not another blank canvas. Groki MCP turns a compact creative brief into **nine private, editable meme directions**: three visual templates across Relatable, Savage, and Unhinged tones. Agents can then inspect a draft, refine exact text or variant choices, and check the connected account's credit balance. ## Remote endpoint ```text https://www.groki.meme/api/mcp ``` - Transport: Streamable HTTP - Authentication: OAuth 2.1 with PKCE and dynamic client registration - Required scopes: `meme:drafts`, `meme:credits` - Product and OAuth guide: https://www.groki.meme/agents MCP-compatible clients should connect to the endpoint and complete the OAuth authorization flow. Do not paste personal access tokens into client configuration. ## Tools | Tool | What it does | | --- | --- | | `create_meme_draft` | Creates nine private meme directions from a brief. One batch costs one Groki credit after a complete brief is supplied | | `get_meme_draft` | Reads an active private draft and its variants for the connected account | | `update_meme_draft` | Applies deterministic text, variant, or brief edits without AI-generation cost | | `get_credit_balance` | Reads the connected Groki account's available credits | ## Example brief ```text Create memes about a Friday production deploy that failed. Make the humor sharp but not mean. Write in English. ``` The agent should ask Groki to create the draft, review the alternatives with the user, and only then choose or edit a variant. ## Safety and privacy - Drafts are private to the connected Groki account - Generating a complete nine-direction batch costs one credit - Incomplete briefs return clarification questions without charging - Updates use optimistic concurrency to prevent an agent from silently overwriting another edit ## Registry metadata The canonical MCP Registry manifest is [`server.json`](./server.json). This repository documents the hosted integration; the product source is not included here.
What people ask about groki-mcp
What is alexclmy/groki-mcp?
+
alexclmy/groki-mcp is subagents for the Claude AI ecosystem with 0 GitHub stars.
How do I install groki-mcp?
+
You can install groki-mcp by cloning the repository (https://github.com/alexclmy/groki-mcp) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is alexclmy/groki-mcp safe to use?
+
Our security agent has analyzed alexclmy/groki-mcp and assigned a Trust Score of 52/100 (tier: OK). See the full breakdown of passed checks and flags on this page.
Who maintains alexclmy/groki-mcp?
+
alexclmy/groki-mcp is maintained by alexclmy. The last recorded GitHub activity is dated 2026-10-01, with 0 open issues.
Are there alternatives to groki-mcp?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy groki-mcp to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/alexclmy-groki-mcp)<a href="https://claudewave.com/repo/alexclmy-groki-mcp"><img src="https://claudewave.com/api/badge/alexclmy-groki-mcp" alt="Featured on ClaudeWave: alexclmy/groki-mcp" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
The agent engineering platform.