Provision an OpenCode workbench and MCP stack on any Linux box, local or over SSH.
One address for any MCP client. No sign-in needed on this server.
4 read6 act
Grouped by tool name. At most: moves money, runs code or commands, deletes data, or sends messages for you.
Odel charges nothing per call. The publisher may charge for its own service.
A reproducible, self-documenting, and recoverable OpenCode development workstation — configuration, agent skills, MCP stack, and an MCP server that clones the entire setup onto any Linux machine (locally or over SSH).
Homepage & remote MCP: https://opencode-workbench.simonmak.com · POST https://opencode-workbench.simonmak.com/mcp
This repository is the single source of truth for a complete cloud development workstation. Everything needed to rebuild from scratch is versioned here:
opencode-workbench — an MCP server that installs this profile on any Linux boxNo important knowledge exists only in human memory.
Register the MCP server with OpenCode:
{
"mcp": {
"opencode-workbench": {
"type": "local",
"command": ["npx", "-y", "@simonmak-ascent/opencode-workbench"],
"enabled": true,
"timeout": 600000
}
}
}
Then ask the agent to run inspect_target → plan_clone → apply_clone { confirm: true } → verify_clone, for { "mode": "local" } or { "mode": "ssh", "host": "<your-box>", "user": "<your-user>" }. apply_clone is consent-gated: without confirm:true it returns a plan (components + privileged-command preview) and changes nothing. Run list_required_credentials to see which keys the box still needs and how to acquire them, and bash scripts/selftest/run-selftest.sh to verify it works. See mcp-server/README.md and docs/architecture/clone-mcp.md.
The clone is key-resilient: with no model key it still boots on the OpenCode Zen free floor, and MCP servers whose credentials are absent are disabled and reported (not left to fail at runtime).
The connector never reads or transmits secret values; it writes an empty ~/.env.workbench template for you to fill in.
Fastest path: no box required — register the MCP server with
npx -y @simonmak-ascent/opencode-workbench (config in
Clone This Workbench); or provision a fresh box:
# Create a new build box
gh SWAS create --repo simonmak-ascent/opencode-workbench --machine basicLinux32gb
# Wait for postCreate (3-5 min) — installs everything automatically
# Then start coding:
opencode
flowchart TB
AGENT["OpenCode agent"] -->|"npx @simonmak-ascent/opencode-workbench"| MCP["opencode-workbench MCP<br/>inspect · plan · apply · verify"]
REPO[("Git repo — single source of truth")] --> MCP
MCP -->|"local or SSH"| BOX["Target Linux box"]
BOX --> PROF["Workstation profile<br/>OpenCode CLI · 35 MCP servers · 45 skills · Docker infra"]
apply_clone is consent-gated: without confirm: true it returns a plan and changes nothing.
sequenceDiagram
autonumber
participant A as OpenCode agent
participant M as opencode-workbench MCP
participant B as Target box (local or SSH)
A->>M: inspect_target
M-->>A: OS, toolchain, Docker, existing config
A->>M: plan_clone
M-->>A: components + privileged-command preview
A->>M: apply_clone { confirm: true }
M->>B: install components · write ~/.env.workbench template
B-->>M: result
A->>M: verify_clone
M-->>A: pass/fail + missing credentials
flowchart LR
A["OpenCode agent"] --> D["Discovery<br/>describe_workbench · inspect_target"]
A --> C["Clone<br/>plan_clone · apply_clone · verify_clone"]
A --> K["Components<br/>install · remove · update_component"]
A --> S["Credentials<br/>list_required_credentials · run_auth_flow"]
opencode-workbench/
├── mcp-server/ # opencode-workbench: clone this profile onto Linux
│ ├── src/ # inspect / plan / apply / verify, local + SSH
│ ├── test/ # unit tests (vitest)
│ └── README.md
├── connector.json # MCP connector manifest / registration snippet
├── plugins/ # memory.ts + doc-tools.ts OpenCode plugins
├── package.json # thin launcher for opencode-workbench (bin + prepare)
├── .devcontainer/ # build box definition & bootstrap
│ ├── devcontainer.json # Container image, features, ports, remoteEnv
│ ├── setup.sh # Post-create: installs opencode, MCPs, Docker infra
│ └── aliases.sh # Shell aliases sourced at runtime
├── .opencode/
│ └── skills/ # 28 custom agent skills (10 research, 10 dev, 8 publishing)
├── vendor/ # Vendored MCP source code
│ ├── perplexity-agent-mcp/
│ └── browserless-mcp/
├── configs/ # Reference configurations
│ ├── mcp/ # MCP server inventory & architecture
│ ├── opencode/ # OpenCode settings documentation
│ ├── shell/ # Shell configuration
│ ├── git/ # Git configuration & hooks
│ └── providers/ # AI provider configuration
├── docs/ # Complete documentation system
│ ├── WORKBENCH_CHARTER.md # Governance: mission, principles, requirements
│ ├── security-model.md # Security architecture & threat model
│ ├── IMPROVEMENT_BACKLOG.md # Tracked improvements and fixes
│ ├── CHANGELOG_WORKBENCH.md # Append-only change history
│ ├── architecture/ # System documentation (incl. clone-mcp.md)
│ ├── recovery/ # Recovery procedures (4 docs)
│ ├── prompts/ # Operational prompt library (9 prompts)
│ └── backup-reports/ # Dated backup snapshots
├── scripts/ # Automation scripts
│ ├── backup/ # Master backup script
│ ├── inventory/ # Auto-generate inventories (software, env, MCP, OpenCode)
│ ├── security/ # Secret pattern scanner
│ ├── recovery/ # Recovery validation
│ └── maintenance/ # Config sync, routine tasks
├── .github/workflows/ # CI (docs, inventory, gitleaks, mcp-server)
├── opencode.json # OpenCode configuration (MCP servers)
├── AGENTS.md # OpenCode agent instructions
└── README.md # This file
| Category | Details |
|---|---|
| OpenCode | Latest stable CLI, DeepSeek V4 Pro model, LSP enabled |
| MCP Servers | 35 configured (33 enabled, 2 disabled), 9 remote + 26 local |
| Agent Skills | 45 reusable skills in .opencode/skills/ |
| Infrastructure | PostgreSQL 16 (Docker), Browserless Chromium (Docker) |
| Tools | pandoc, jq, miller, sqlite3, GitHub CLI, Playwright Chromium |
| Prompts | 9 operational prompts in docs/prompts/ |
This workstation operates under a formal charter. Key principles:
Read the full charter: docs/WORKBENCH_CHARTER.md
# Master backup — full inventory, security scan, commit prep
bash scripts/backup/run-master-backup.sh
# Quick backup — save state before risky operations
bash scripts/maintenance/sync-runtime-config.sh && \
git diff > /tmp/quick-backup-$(date +%Y%m%d).diff
Or use OpenCode prompts:
docs/prompts/RUN_MASTER_BACKUP.md — execute backup via AIdocs/prompts/QUICK_BACKUP.md — rapid state preservationAssume the build box is deleted. Only Git repo + build box Secrets survive.
# 1. Create new build box
gh SWAS create --repo simonmak-ascent/opencode-workbench --machine basicLinux32gb
# 2. Wait for automation (3-5 min)
# 3. If needed (usually done by setup.sh):
npx playwright install chromium
# Vercel MCP uses VERCEL_ACCESS_TOKEN (token auth — no OAuth step)
# 4. Validate recovery
bash scripts/recovery/validate-recovery.sh
Full details: docs/recovery/RECOVERY_PLAYBOOK.md
| Type | Count | Notes |
|---|---|---|
| Remote | 9 | context7, gh_grep, vdd, exa, cloudflare, clerk, vercel (token auth), sentry, stripe |
| Local | 26 | npm / vendored / binary stdio servers |
Totals: 35 configured (33 enabled, 2 disabled: google-search, google-workspace).
See: docs/architecture/mcp-inventory.md
All secrets stored in the build box Secrets. Never in repository files.
| # | Secret | Used By |
|---|---|---|
| 1 | DEEPSEEK_API_KEY | OpenCode (primary model) |
| 2 | OPENCODE_API_KEY | OpenCode Zen / Console Go providers |
| 3 | SIMONMAK_ASCENT_PAT | GitHub MCP, shadcn MCP, gh |
| 4 | PERPLEXITY_API_KEY | Perplexity MCP |
| 5 | BRAVE_API_KEY | Brave Search MCP |
| 6 | BROWSERLESS_TOKEN | Browserless MCP + container |
| 7 | SENTRY_AUTH_TOKEN | Sentry MCP |
| 8 | VERCEL_ACCESS_TOKEN | Vercel MCP (token auth) |
Additional keys for opt-in servers (EXA_API_KEY, CLOUDFLARE_API_TOKEN,
STRIPE_SECRET_KEY, SURREAL_*, ALIBABA_CLOUD_*, AZURE_*, FIRECRAWL_API_KEY,
FRED_API_KEY, COMPANIES_HOUSE_API_KEY) are catalogued in
docs/architecture/secrets.md — never by value.
See: docs/architecture/secrets.md
| Document | Purpose |
|---|---|
docs/WORKBENCH_CHARTER.md | Mission, principles, governance |
docs/security-model.md | Security architecture, threat model, incident response |
docs/IMPROVEMENT_BACKLOG.md | Tracked improvements and technical debt |
docs/CHANGELOG_WORKBENCH.md | Complete change history |
docs/architecture/ | System documentation (10 inventory docs) |
docs/recovery/ | Recovery playbook, disaster recovery, checklist, gap analysis |
docs/prompts/ | 9 operational prompts with index |
docs/backup-reports/ | Dated backup snapshots |
.devcontainer/setup.sh, add to opencode.json, document in docs/architecture/mcp-inventory.md.opencode/skills/<name>/SKILL.md, follow naming conventionscripts/bootstrap-tools.shdocs/prompts/, update prompt-index.mdCHANGELOG_WORKBENCH.md, run master backupValidated disaster recovery within < 10 minutes using repository + build box Secrets alone.
Up-to-date OpenCode Workbench documentation is indexed on Context7, so coding agents can pull it into context on demand. With the Context7 MCP server or ctx7 CLI installed, name the library in your prompt:
use library /simonmak-ascent/opencode-workbench for API and docs
MIT — see LICENSE.
A tool by Simon Mak.
If this saves you time, a ⭐ on GitHub helps others find it.