Spin up a complete OpenCode development environment on any Linux box — one agent-driven workflow, six tools, zero secrets.
Scored across 10 tools
The set is built around a clear lifecycle (describe → inspect → plan → apply → verify) and the descriptions explicitly cross-reference each other to disambiguate look-alikes such as plan_clone vs inspect_target vs verify_clone. Some residual overlap remains among the read-only probe tools, but each has a distinguishable output contract and intended moment of use.
Every tool is snake_case verb_noun (apply_clone, install_component, remove_component, list_required_credentials, run_auth_flow), with no style mixing. The verbs map predictably onto actions (install/update/remove, plan/apply/verify).
Ten tools for a provisioning server is well-scoped: a full profile flow plus single-component install/update/remove and a credential sub-flow. No tool appears redundant or vestigial at the count level.
The lifecycle is well covered: discovery, target inspection, dry-run planning, apply, per-component install/update/remove, post-apply verification, and credential listing/acquisition guidance. Minor gaps exist around editing config or profile files directly and acting on credentials (run_auth_flow only emits guidance and cannot persist values).
Apply the Workbench profile to a target: clone the repo and install missing components (OpenCode CLI, Node/pnpm, MCP servers, skills, plugins, optional Docker). It OVERWRITES <home>/.config/opencode/opencode.json, copies AGENTS.md, resets an existing profile repo to origin/main, and runs global installs that need write permission (plus SSH for mode:ssh) and can take minutes. Writes a names-only ~/.env.workbench (mode 600); never secret values. Consent-gated and idempotent: without confirm:true it returns the plan and changes nothing. Parameter semantics: components defaults to required+core; workspace defaults to ~/opencode-workbench; skipRepo skips the clone/update; profileUrl overrides the git remote; dryRun returns the plan. To preview only, use plan_clone.
Inputs: target (required), dryRun, confirm, skipRepo, +3 more. Returns: plan, model, dryRun, target, +9 more
Describe this MCP server from its bundled profile without contacting any target or making a network call: repository URL, the default component set, components grouped by tier (required/core/optional), and optional MCP add-ons. It takes no parameters, is always safe, and returns instantly. Use it first to resolve a component id for install_component/remove_component/update_component or to see available add-ons; use inspect_target for a machine's live state.
Inputs: no named parameters. Returns: repo, repoGit, versions, components, +3 more
Probe one Linux machine — this host (local) or a remote host over SSH (ssh) — and report its OS, kernel, architecture, package manager, Node/npm, OpenCode, Docker, and per-tool detection flags, plus the names (never values) of credentials present. Read-only: it runs one shell probe as the target user (over SSH when mode:ssh), installs nothing, writes nothing, contacts no external service, and can take a few seconds per hop. Parameter semantics: target.mode selects local vs ssh (default local); target.host is required only for ssh; target.user defaults to the ssh config/current user; target.cwd sets the directory for relative checks; target.port/identityFile pass straight to ssh. Use it to see what a clone would touch, then plan_clone to turn that into an ordered plan and apply_clone to perform it.
Inputs: target (required). Returns: has, arch, home, osId, +17 more
Install a single Workbench component by id (e.g. node, opencode, npm-mcps, skills) on a target; component must be an id from describe_workbench. Overwrites that component's files when present (e.g. skills/plugins replace the copies under <home>/.config/opencode); global installs need write permission and can take minutes. Idempotent and consent-gated: without confirm:true it returns the plan. Parameter semantics: component is required; workspace defaults to ~/opencode-workbench; confirm defaults to false (plan only). Use it for one targeted component; use apply_clone to install the full default set.
Inputs: target (required), component (required), confirm, workspace. Returns: plan, model, dryRun, target, +9 more
List the credentials the profile references, which the target already provides, and how to acquire each missing one. Value-blind: it reads only whether each env var is set — no values, no network, no writes — via one read-only probe. Parameter semantics: target selects the machine (local or SSH) and its home sets the returned template path and the env file the presence check reads; there are no other parameters. Returns present/missing var-name arrays plus one guidance record per credential (var, purpose, url, method, command). Use it after plan_clone to see what would degrade; act on one credential with run_auth_flow.
Inputs: target (required). Returns: target, missing, present, template, +1 more
Return a read-only plan for a target: compare it against the Workbench profile and list each component as install, present, or manual, with the commands that would run. It still runs a detection probe on the target (same access as inspect_target) but clones nothing and writes nothing. Parameter semantics: components restricts the diff to those ids (default: required+core); workspace sets the expected profile path on the target (default ~/opencode-workbench); profileUrl overrides the git remote. Use it to preview before apply_clone, which performs the changes.
Inputs: target (required), dryRun, skipRepo, workspace, +2 more. Returns: steps, target, inspect, toInstall
Uninstall one Workbench component by id from a target — the inverse of install_component — for a bounded, documented subset with an automated uninstall (e.g. opencode, pnpm, npm-mcps, skills, docker-containers); component must be an id from describe_workbench. Idempotent: an already-absent component reports absent; a component with no automated uninstall (system packages such as git/curl/node) reports manual. Destructive and consent-gated: without confirm:true it returns a preview and changes nothing, and it deletes only that component's files — never opencode.json or the profile repo. Parameter semantics: workspace sets the profile path some removals need; dryRun reports without changing. Use it to tear down one component; for several, call it per id.
Inputs: target (required), component (required), dryRun, confirm, +1 more. Returns: id, code, action, output, +2 more
Return the acquisition plan for one credential on a target: the provider URL, the exact non-interactive command when one exists (e.g. opencode auth login, opencode mcp auth vercel, gh auth login), and whether it is already present. Read-only and value-blind: it emits guidance and re-checks presence with one read-only probe; it does not run the commands or handle secret values. Parameter semantics: var must be an env var name returned by list_required_credentials (unknown names error); target selects the machine and its home is where the value should be written. Use it for a single credential; it does not replace that listing.
Inputs: var (required), target (required). Returns: url, var, next, method, +4 more
Update one Workbench component in place by id: re-run its install script to fetch the current version (e.g. opencode re-runs the official installer; npm-mcps reinstalls the latest globals). It OVERWRITES the component's files, needs write permission, and can take minutes for global installs; the resolved version may change. Parameter semantics: component must be an id from describe_workbench; workspace defaults to ~/opencode-workbench; dryRun previews; confirm defaults to false — set confirm:true to apply. For the whole profile use apply_clone.
Inputs: target (required), component (required), dryRun, confirm, +1 more. Returns: id, code, action, output, +2 more
Re-check a target after a clone: return a per-component present/missing list plus whether opencode.json and ~/.env.workbench exist. Read-only and idempotent: it runs a detection probe (SSH or local) and checks files, writing nothing. target selects the machine (local or SSH) and its home is where the opencode.json and ~/.env.workbench checks run; components restricts the check to those ids (omit it to check every component, the default); workspace sets the profile path used by component checks. Use it after apply_clone and after component changes; for a pre-clone preview use plan_clone.
Inputs: target (required), dryRun, skipRepo, workspace, +2 more. Returns: target, missing, envExists, components, +1 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Add one secure layer between your agents and this server.
