MCP server for deploying and managing AI-generated projects to live HTTPS URLs with hot-reload sandbox support, access control, and resource management.
OpenBerth MCP provides 19 well-structured deployment and sandbox management tools with comprehensive descriptions and input schemas. Tool names follow verb_noun convention (deploy, update, destroy, protect, lock, sandbox_*). Descriptions are detailed (100-300 chars typical) and include WHEN to use each tool vs. alternatives (e.g., 'use berth_sandbox_create for iteration, berth_deploy for one-time deploys'). All parameters have type definitions and descriptions. However, output schemas are not documented in the source, responses are inferred from tool names and descriptions. Error handling guidance is minimal. Some parameter descriptions could be more prescriptive about constraints (e.g., exact TTL format, memory unit validation). Tool composition is strong: deploy/update/destroy form a clear lifecycle; sandbox_* tools are well-separated from production tools.
Deploy a small set of AI-generated files to a live HTTPS URL. Provide files as a map of filepath to content. Best for 1-100 files generated in conversation. For iterative development where you'll make multiple changes, use berth_sandbox_create instead — it supports instant hot-reload without full rebuilds. Framework is auto-detected. If detection fails, include a .berth.json file with override fields (language, build, start, install, dev).
Deploy a project directory from the local filesystem to a live HTTPS URL. Creates a tarball and uploads it. Respects .gitignore. PREFERRED over berth_deploy when: - The project already exists on disk (user said "deploy this", "deploy my app", referenced a path) - The project has more than 5 files - The project has dependencies (node_modules, venv, etc.) that shouldn't be sent inline For iterative development where you'll make multiple changes, use berth_sandbox_create instead.
Destroy a deployment and free its resources. This permanently removes the deployment, its container, data, and URL.
List active deployments. By default returns the caller's own deployments. Pass `all: true` to list every deployment on the server (read visibility is open — each entry includes `ownerId`/`ownerName`). Mutation still requires ownership or admin. Use this to find existing deployments before creating new ones. If the user wants to update an existing app, find it here first rather than creating a duplicate.
Output schemas not documented. Tool descriptions infer return types (e.g., 'Get the status... returns status values'), but no formal response schema is visible in source. LLMs cannot plan downstream tool calls without knowing what fields to extract.
Parameter constraints not formalized. TTL values described as '24h', '7d', '0' but no regex pattern or enum. Memory limits described as '512m', '1g' but no validation rule. LLMs may pass invalid formats like '512mb' or '1 gb'.
Error handling guidance absent. No tool description explains what to do if a deployment fails, a secret is not found, or a resource is locked. Descriptions state WHAT the tool does but not how to recover from errors.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 66 | 2026-07-28+ | v2 |
Lock or unlock a deployment. A locked deployment keeps running and serving traffic, but rejects all code updates, metadata changes, access control changes, and destroy until unlocked. Use this to freeze a stable deployment and prevent accidental changes.
Get the container logs for a deployment. Useful for debugging build or runtime errors. ALWAYS check logs when: - A deployment status is 'failed' - The deployed app shows errors or blank pages - You need to debug application behavior Logs include both build output and runtime output.
Set access control on a deployment. Modes: 'basic_auth' (browser password prompt), 'api_key' (header auth), 'user' (require OpenBerth login), 'public' (remove protection). For basic_auth, provide username and password. For api_key, an API key is auto-generated if not provided — use it via the 'X-Api-Key' header. For 'user' mode, optionally provide a 'users' list to restrict access to specific usernames — if omitted, any authenticated user can access. Use 'public' to remove any existing protection.
Set or remove network transfer quota for a deployment. Quota is enforced at the container level.
Create a live development sandbox with hot reload. File changes via berth_sandbox_push apply instantly — no full rebuild needed. USE SANDBOX (not deploy) when: - The user wants to iterate on code (they'll make multiple changes) - You're building something step-by-step - You want to test changes quickly before finalizing Supports: static HTML, Node.js (Vite/Next.js/Nuxt/SvelteKit), Python (FastAPI/Flask/Django), Go. After creation, use berth_sandbox_push to update files instantly. When done iterating, use berth_sandbox_promote to create an optimized production deployment. Framework is auto-detected. If detection fails, include a .berth.json file with override fields (language, build, start, install, dev).
Promote a sandbox to a production deployment. Creates an optimized build (minified, tree-shaken, etc.) and a new permanent deployment URL. Use this when you're done iterating and want to finalize the app.
Push file changes to a running sandbox. Changes apply instantly via HMR (Node/Vite) or trigger automatic rebuild (Go, Python). No full container rebuild needed. If you modify dependency files (package.json, requirements.txt, go.mod), dependencies are reinstalled automatically.
Delete a secret. This removes it from the server and any deployments using it will no longer have access to it.
List all available secrets. Returns secret names and descriptions (not values). Use secret names with the 'secrets' parameter in deploy/update/sandbox tools.
Create or update a secret. Secrets are stored server-side and injected as environment variables at runtime. Values are never exposed to the client.
Get the source code files of a deployment. Returns all text files and their contents. Use this to inspect what code is running in a deployment. Requires the deployment ID. Use berth_update to modify and redeploy.
Get live resource usage stats for a deployment: CPU, memory, storage, bandwidth. Requires ownership or admin access.
Get the status of a deployment (building, running, failed, etc.) and its URL. Use this after berth_deploy or berth_update to check if the build completed. Status values: 'building' (wait and check again), 'running' (ready to use), 'failed' (check berth_logs for errors).
Update an existing deployment with new inline files. Replaces all files and triggers a full rebuild. For iterative changes to a sandbox, use berth_sandbox_push — it's instant (no rebuild).
Update an existing deployment from a local project directory. Creates a tarball and uploads it. Respects .gitignore. PREFERRED over berth_update when the project exists on disk.
Destructive operations lack confirmation step. berth_destroy and berth_secret_delete are irreversible but have no dry-run or confirmation mechanism. An agent mistake could permanently delete a deployment.
Pagination not documented for berth_list. Description does not mention result limits, total count, or next_cursor. If a user has many deployments, the response could be truncated without the LLM knowing.