workflowstacks
mcp-server

agentdock

Secure MCP runtime for AI agents to operate local machines, servers, and containers with multi-device orchestration.
1,271 stars+25★ this week164 forksGoUpdated 10/20/2026100% free · open source
What it does

AgentDock runs a secure MCP (Multi‑Device Compute Protocol) runtime that lets AI agents safely execute code on your local machine, servers, or containers.

When to use it
  • •You need an isolated, controllable environment where an LLM‑driven agent can run shell commands or Docker containers without giving it unrestricted host access.
  • •Your product launches AI‑powered automation (e.g., data pipelines, image processing) and you want to orchestrate those jobs across multiple machines from a single control plane.
  • •You want to test AI‑agent code locally before promoting it to a cloud‑hosted MCP server.
Ready-to-paste prompt
mcp exec --image node:20-alpine --cmd "node -e 'console.log("AgentDock executed a Node script!")'" --env API_KEY=abcd1234
Heads up: AgentDock requires a valid `--auth-token` (or `MCP_TOKEN` env var) for every client request; if the token is missing or mismatched the server will reject all commands.
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/agentdock && curl -fsSL https://workflowstacks.com/api/skills/agentdock/claude-skill -o ~/.claude/skills/agentdock/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How agentdock works
Codeflow
Free to inspect

Agentdock is a very large Go project (~134k lines across 841 code files, plus 45 test files). Setup is light: installs like a normal app — add your API keys. Reading the code is optional. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~134k lines · 841 code files · days to read — use, don't read
Setup
One-command install
Installs like a normal app — add your API keys. Reading the code is optional.
Runs on
Go · Docker
Needs API keys (.env)
Go 77%Swift 8%PowerShell 7%C# 5%Shell 2%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    cmd/agentdock/main.go
    Where the program starts running
  3. 3
    go.mod
    Dependencies and the commands it exposes
  4. 4
    .env.example
    The API keys and settings you must provide
  5. 5
    internal/acp/adapter_identity_test.go
    Inside internal/ — the main logic begins here
What's in each folder
internal/Core code — the actual logic731 files
core-skills/Prompts, skills & agent definitions15 files
cmd/Command-line entry points28 files
docs/Documentation14 files
desktop/Folder76 files
scripts/Helper scripts45 files
packaging/Folder22 files
tools/Helper scripts11 files
READMEHas testsDocumentedCI checksDocker readyApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
uvwt
Language
Go
Category
mcp-server
Published
5/25/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/agentdock.svg)](https://workflowstacks.com/skills/agentdock?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 375,248
Rea: Reverse Engineer Apps
Inspect apps down to binary level with Rea. For founders needing code clarity.
mcp-server★ 287,609
ECC supercharges AI‑agent performance for founders building Claude, Codex, and Cursor
Founders gain optimized skills, memory, security, and research‑first development for Claude Code, Codex, Opencode, Cursor, backed by 280k+ GitHub stars.
mcp-server★ 156,600
open-webui: Self‑hosted AI Chat UI for Faster LLM Integration
Launch a sleek, web‑based AI interface that works with Ollama, OpenAI API, and more—ideal for founders needing a quick, customizable LLM front‑end. 153k+ GitHub stars.
mcp-server★ 21,172
jcode: Boost Coding
Harness coding power with jcode, a tool for founders, backed by 6.9k+ GitHub stars.
mcp-server★ 13,068
QuantDinger: AI‑Powered Trading Engine for Crypto, Stocks & Forex
Launch data‑driven strategies with QuantDinger’s backtesting, live‑trade execution and multi‑agent research—all in Python. Ideal for fintech founders seeking scalable, AI‑enhanced trading solutions. 13k+ GitHub stars.
mcp-server★ 1,488
lime – Streamlined AI workspace for Chinese creators
Boost your content pipeline with lime’s desktop writing, research, prompt library, and knowledge‑base tools, built for Chinese creators. 1.5k+ GitHub stars.