Log inSubmit server
Opencode Workbench logo

Opencode Workbench

Provision and recover an OpenCode workstation on local or SSH-accessed Linux machines through MCP tools.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Opencode Workbench

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "opencode-workbench": {
      "command": "npx",
      "args": [
        "-y",
        "@simonmak-ascent/opencode-workbench"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 10 tools correctly (Today).

Overview

The opencode-workbench MCP server provisions a versioned OpenCode workstation profile on a local or SSH-accessed Linux machine. It inspects the target, creates a clone plan, applies approved changes, and verifies the result through MCP tools. The profile can include OpenCode, configured MCP servers, agent skills, Docker infrastructure, and supporting tools. Reach for it when you need to reproduce a documented development workstation or recover one without manually rebuilding each component.

Use cases

  • Provision a reproducible OpenCode workstation on Linux
  • Clone the profile to a remote machine over SSH
  • Inspect a target before changing its configuration
  • Review privileged commands before applying a clone
  • Verify a recovered workstation and identify missing credentials

Key features

  • Local and SSH-based Linux provisioning
  • Consent-gated clone planning and application
  • Target inspection and post-install verification
  • Component install, removal, and updates
  • Credential requirement reporting without secret transmission
  • OpenCode workstation profile with MCP servers and agent skills

Tools10

What Opencode Workbench lets your agent do. Expand a tool for its parameters.

Verified live~4.2k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

4/4 checks healthy over the last 14d

What it can do

From the 10 tools this server returned when we ran it; 10 declare their own safety hints.

Runs commands · 1Can delete or modify data · 4Handles credentials · 5Makes network requests · 10Read-only tools · 5
Unusual tool instructions. 2 tool descriptions contain text aimed at the AI model rather than at you (reaches for local secrets). Read the tool descriptions before connecting.
Network at startup3 connections
Files written at startupNone
Install scriptsprepare
npm provenanceNot published
Package age27 days
Maintainers1

Observed 2026-10-30 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 15d ago via OSV.dev · @simonmak-ascent/opencode-workbench (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1Stargazers on the source repository.
npm downloads2.3kPackage downloads in the last 30 days.
Last commit2d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed10Callable tools this server registers over MCP.

How Opencode Workbench works

What opencode-workbench does

The opencode-workbench MCP server installs the repository’s workstation profile on a Linux target. The profile includes OpenCode configuration, MCP server configuration, reusable agent skills, Docker-based infrastructure, command-line tools, and operational documentation. It is intended to make a development environment reproducible from the repository’s versioned configuration.

The target can be the machine running the connector or another Linux machine accessed through SSH. The setup can include PostgreSQL 16 and Browserless Chromium through Docker, along with tools such as pandoc, jq, Miller, sqlite3, the GitHub CLI, and Playwright Chromium, as described by the repository.

This project belongs to the 💻 Developer Tools category and is most relevant when a team needs a repeatable OpenCode workstation, a documented recovery path, or a way to bootstrap a fresh Linux box.

How it works

The opencode-workbench MCP server exposes a staged clone lifecycle. inspect_target reports information about the target, including its operating system, available toolchain, Docker state, and existing configuration. plan_clone then produces the proposed components and a preview of privileged commands.

apply_clone performs the changes only when called with confirm: true. Without that confirmation, it returns the plan and does not modify the machine. Afterward, verify_clone checks the result and reports pass/fail information together with missing credentials.

The connector does not read or transmit secret values. During provisioning it writes an empty ~/.env.workbench template for the operator to complete. Missing model or service credentials do not necessarily prevent the workstation from booting: unavailable credential-dependent MCP servers are disabled and reported, while the setup can use the OpenCode Zen free floor when no model key is present.

Setup and configuration

For a local OpenCode registration, configure the server to run through npx -y @simonmak-ascent/opencode-workbench. The example configuration enables the server and sets a 600-second timeout. The project also publishes a remote MCP endpoint at POST https://opencode-workbench.simonmak.com/mcp.

After registration, ask the OpenCode agent to run inspect_target, plan_clone, apply_clone with confirmation, and verify_clone. Use { "mode": "local" } for the current machine or { "mode": "ssh", "host": "...", "user": "..." } for an SSH target. list_required_credentials identifies keys still needed and explains how to obtain them; run_auth_flow is available for credential-related flows.

Run bash scripts/selftest/run-selftest.sh to perform the repository’s self-test.

Tools and capabilities

The documented tool surface includes:

  • describe_workbench for discovering the available workbench profile.
  • inspect_target for examining the destination machine.
  • plan_clone for generating a change plan and privileged-command preview.
  • apply_clone for applying a confirmed plan.
  • verify_clone for checking installation results.
  • install, remove, and update_component for component management.
  • list_required_credentials and run_auth_flow for credential-related tasks.

The server supports both local and SSH-based clone operations. Its profile covers 35 configured MCP servers, with 33 enabled and 2 disabled in the referenced configuration, plus 45 reusable skills and OpenCode plugins. Exact components can change with the repository’s source-of-truth configuration.

Limitations and notes

The target must be a Linux machine, and SSH mode requires a reachable host and usable SSH access. Applying a clone can run privileged commands, so the confirmation step should be reviewed rather than treated as an automatic installation approval.

The connector intentionally does not handle secret values. Operators must fill in the generated environment template and provide any required credentials separately. Services without credentials are disabled and reported rather than guaranteed to work immediately.

Other MCP clients may require their own local or remote MCP configuration format.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Opencode Workbench

opencode-workbench is an MCP server that connects an OpenCode agent to a versioned workstation profile and a local or SSH-accessed Linux machine. Its main tools inspect targets, plan and apply confirmed clones, verify results, manage components, describe the workbench, and report required credentials without transmitting secret values.

Install it by registering `npx -y @simonmak-ascent/opencode-workbench` as a local MCP server in OpenCode. Enable the entry and set the documented 600-second timeout, then use the clone lifecycle tools to inspect, plan, apply with confirmation, and verify the target.

Yes, it can provision a remote Linux machine over SSH. Pass `mode: "ssh"` with the target `host` and `user`; use `mode: "local"` for the machine running the connector.

Not necessarily for initial boot. With no model key, the workstation can use the OpenCode Zen free floor, while MCP servers lacking credentials are disabled and reported. The connector writes an empty `~/.env.workbench` template and does not read or transmit secret values.

It documents OpenCode registration through a local `npx` command and also lists a remote MCP endpoint, so Cursor users would need to apply the client’s own MCP configuration format.

Related MCP servers

All in Developer Tools All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewOpencode Workbench AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/opencode-workbench?style=directory)](https://allmcps.com/mcp/opencode-workbench)
HTML Embed
<a href="https://allmcps.com/mcp/opencode-workbench"><img src="https://allmcps.com/api/badge/opencode-workbench?style=directory" alt="Opencode Workbench on AllMCPs" /></a>