Hotkeyless Ahk Mcp

Created By
tim0-124322 months ago
MCP server for Hotkeyless AHK HTTP API. It lets your agent control your whole computer through hotkeys.
Overview

Hotkeyless AHK MCP and Skills

License: MIT AHK Version MCP Claude Support OpenCode Support Github Copilot Support

This repository provides:

  • A TypeScript MCP server that wraps the Hotkeyless AHK HTTP API.
  • Reusable skill documents for OpenCode, Claude, and generic agent runtimes.
  • Practical examples for desktop automation scenarios.

Workspace layout

packages/
  mcp-server/   # Node MCP server package
  skills/       # Agent skill documents
examples/       # End-to-end usage examples

  1. MCP server
  1. Agent skills

MCP server

Quick start

OpenCode

opencode.json:

{
  ...
  "mcp": {
    ...
    "hotkeyless-ahk": {
      "type": "local",
      "command": ["npx", "-y", "@tim0_12432/hotkeyless-ahk-mcp-server"],
      "enabled": true,
      "environment": {
          "BLACKLIST": "shutdown,restart,kill"
          ...
      }
    }
  },
  ...
}

ClaudeCode

.mcp.json:

{
  "mcpServers": {
    ...
    "hotkeyless-ahk": {
      "command": "npx",
      "args": ["-y", "@tim0_12432/hotkeyless-ahk-mcp-server"],
      "env": {
        "BLACKLIST": "shutdown,restart,kill"
        ...
      }
    }
  }
}

Github Copilot

mcp-config.json:

{
  ...
  "mcpServers": {
    ...
    "hotkeyless-ahk": {
      "type": "local",
      "command": "npx",
      "args": ["-y", "@tim0_12432/hotkeyless-ahk-mcp-server"],
      "env": {
        "BLACKLIST": "shutdown,restart,kill"
          ...
      },
      "tools": ["*"]
    }
  },
  ...
}

Build from source

Follow instructions here.

1. Build server

bun install
bun run build

npm should also work without problems!

2. Setup your harness

OpenCode

opencode.json:

{
  ...
  "mcp": {
    ...
    "hotkeyless-ahk": {
      "type": "local",
      "command": ["node", "<absolute path to the built files>/mcp-server/dist/index.js"],
      "enabled": true,
      "environment": {
          "BLACKLIST": "shutdown,restart,kill"
          ...
      }
    }
  },
  ...
}
ClaudeCode

.mcp.json:

{
  "mcpServers": {
    ...
    "hotkeyless-ahk": {
      "command": "node",
      "args": ["<absolute path to the built files>/mcp-server/dist/index.js"],
      "env": {
        "BLACKLIST": "shutdown,restart,kill"
        ...
      }
    }
  }
}
Github Copilot

mcp-config.json:

{
  ...
  "mcpServers": {
    ...
    "hotkeyless-ahk": {
      "type": "local",
      "command": "node",
      "args": ["<absolute path to the built files>/mcp-server/dist/index.js"],
      "env": {
        "BLACKLIST": "shutdown,restart,kill"
          ...
      },
      "tools": ["*"]
    }
  },
  ...
}

Hotkeyless AHK API contract

  • GET /list returns JSON array of { command: string, note: string }
  • GET /send/<command> accepts query parameters

Configuration

Default config is at mcp-server/dist/infrastructure/config/config.ts.

Environment overrides:

Parameter overrideWhat it doesDefault
BASE_URLAdress of the Hotkeyless AHK serverhttp://localhost:42800
TIMEOUT_MSTimeout milliseconds for each request4000
BLACKLISTA list of commands to avoid being called[]
CACHE_TTL_MSCache lifetime for command list in milliseconds5000
ENDPOINT_LISTEndpoint address of the command list/list
ENDPOINT_TRIGGEREndpoint address for invoking commands/send

Agent Skills

Quick start

OpenCode

  1. Copy the ./skills/.opencode/... folders to
  • .opencode/skills for project specific skill setup
  • %USERPROFILE%/.config/opencode/skills for global setup
  1. You can adjust AGENTS.md, custom subagents or custom commands to reference the skills
  2. Restart your OpenCode (CLI or Desktop)
  3. When asking the agent to use the "hotkeyless AHK skills" it should now use the skill guide

ClaudeCode

  1. Copy the ./skills/.claude/... folders to
  • .claude/skills for project specific skill setup
  • %USERPROFILE%/.config/claude-code/skills for global setup
  1. You can adjust CLAUDE.md, custom subagents or custom commands to reference the skills
  2. Restart your Claude Code
  3. When asking the agent to use the "hotkeyless AHK skills" it should now use the skill guide

Github Copilot

  1. Copy the ./skills/.claude/... folders to
  • .claude/skills for project specific skill setup
  • %USERPROFILE%/.config/claude-code/skills for global setup
  1. You can adjust AGENTS.md, custom subagents or custom commands to reference the skills
  2. Restart your Claude Code
  3. When asking the agent to use the "hotkeyless AHK skills" it should now use the skill guide

License

MIT

Server Config

{
  "mcpServers": {
    "hotkeyless-ahk": {
      "command": "npx",
      "args": [
        "-y",
        "@tim0_12432/hotkeyless-ahk-mcp-server"
      ],
      "env": {
        "BLACKLIST": "shutdown,restart,kill,..."
      }
    }
  }
}
Project Info
Created At
2 months ago
Updated At
a month ago
Author Name
tim0-12432
Star
-
Language
-
License
-
Category

Recommend Servers

View All
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

11 hours ago
Tavily Mcp
@tavily-ai

JavaScript
a year ago
Puter Mcp

2 days ago
Linkpulse

14 hours ago