Ashlr Workbench MCP Server

Your local coding-agent HQ — four agents, one local LLM, ten MCP servers, zero cloud dependencies.

Local serverstdioPython

What is the Ashlr Workbench MCP server?

Most AI and media services work still happens through a UI a human drives. Ashlr Workbench MCP server moves it into the conversation instead. Your local coding-agent HQ — four agents, one local LLM, ten MCP servers, zero cloud dependencies.

The tools it exposes

The server publishes 1 tool. What each one is for:

  • Scenario — Best agent

What it needs from you

Configuration is passed through the environment: GITHUB_TOKEN, XAI_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  • macOS 14+ (Apple Silicon recommended; Intel works but slower) - Docker Desktop — for OpenHands - LM Studio with qwen/qwen3-coder-30b loaded — primary LLM - Bun ≥ 1.1 — for ashlr-plugin MCP servers and ashlrcode - Python 3.12+ — for Aider - Node ≥ 20 / npm — for npm install -g ashlrcode - ~32 GB free RAM (Qwen3-Coder-30B in 4-bit needs ~24 GB live) - ~30 GB free disk

Getting it running

The server ships on npm as ashlrcode, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

How it compares

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Ashlr Workbench's toolset — Scenario — is a fair guide to whether it matches your workflow. It is maintained by ashlrai; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
ScenarioBest agent

How to install the Ashlr Workbench MCP server

{
  "mcpServers": {
    "ashlr-workbench": {
      "command": "npx",
      "args": ["-y", "ashlrcode"],
      "env": {
        "GITHUB_TOKEN": "your-value",
        "XAI_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • macOS 14+ (Apple Silicon recommended; Intel works but slower) - Docker Desktop — for OpenHands - LM Studio with qwen/qwen3-coder-30b loaded — primary LLM - Bun ≥ 1.1 — for ashlr-plugin MCP servers and ashlrcode - Python 3.12+ — for Aider - Node ≥ 20 / npm — for npm install -g ashlrcode - ~32 GB free RAM (Qwen3-Coder-30B in 4-bit needs ~24 GB live) - ~30 GB free disk
VariableDescriptionRequired
GITHUB_TOKENCredential the server authenticates with.Yes
XAI_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Ashlr Workbench to Scenario.

Frequently asked questions

It connects Ashlr Workbench to MCP-compatible AI assistants such as Claude and Cursor, exposing 1 tool (Scenario) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Ashlr Workbench directly.