When to use ohmyho.st
Use ohmyho.st when the customer wants to develop or deploy an app using its managed versions or selected GitHub source; inspect a project’s deployment, database or DNS/mail readiness; manage usage and budgets; or request an encrypted SQL export. Use the transport and operations available in this client. Your agent follows the get-started Skill for installation, sign-in and workspace selection before its first deployment (what it covers). Once connected, follow the first deployment quickstart to publish a Dev preview. To call the same operations from a script, see the REST API authentication example. Ask which account is signed in to read its current email and scoped workspace IDs and names throughidentity_get, on either transport. A user API token identifies its owner; machine-to-machine credentials have a null email. Current account details.
Start with identity_get, then select the customer’s project with the available list tool: remote project_list or local projects_list. Read project_context_get and source_get before acting. Use include_binding: true on source_get before using connection/generation guards. Default GitHub reads preserve their existing status fields; managed reads always include the full binding. The server’s current source binding is authoritative; an agent’s location or copied Git remote does not replace it. A new app developed entirely in chat starts with managed versions, while an explicitly selected GitHub repository uses GitHub. Configure only the capabilities the application needs and keep its chosen authentication provider. Use the matching task Skill for the workflow.
For a new project, ask whether Dev should be protected or public before project_create; protected is the default. project_dev_share_link_get returns the Owner’s reusable protected link. The named project_dev_access_mode_set tool changes the choice, while project_dev_share_link_rotate and project_dev_share_link_revoke block old links and browser sessions on their next request. Discover the connected client’s actual tools before requesting those changes. Dev access details.
When the client’s tools support the requested custom domain before the first Prod deployment, use domain_paid_plan and domain_paid_apply to reserve it, then domain_cloudflare_authorize and domain_cloudflare_status for scoped consent. awaiting_deployment means no DNS or certificate provisioning has started. Deploy and verify the Prod hosting address, then repeat domain_paid_apply with the original hostname and idempotency key. Consent and deployment alone do not activate it. Domain setup.
Configure application authentication
Choose the provider for your app’s users. The MCP connection establishes your agent’s hosting identity. Follow the application authentication guide to select and implement end-user sign-in. For Omh Native Auth, use an approved Paid project as its Owner and verify the sender and application identity. Choose Dev or Prod and use itsproject_id and environment_id with these tools in either MCP transport:
- Call
native_auth_config_getfor the current configuration and readiness. - Call
native_auth_config_setwith the currentconfiguration_revision, the intended settings and anidempotency_key. Keep that key for a retry if the outcome is uncertain. - Deploy the app with
auth.provider: omh-native, then callnative_auth_config_getagain. Check all four readiness fields and verify password sign-in on the deployed app. Repeat separately for Prod.
callbackUrl via native_auth_provider_get and have the customer register it in their own OAuth app. Call native_auth_provider_secret_input_request with the current configuration revision from native_auth_config_get, the provider, the Client ID and enabled: true. The Client Secret goes into the protected ten-minute portal link in remote MCP, or into the supplied stdin-only command in local MCP. In remote MCP, read the result via connection_status. Check provider status and verify a full login in the chosen environment. Use native_auth_provider_set for changes that need no new secret. Availability and provider setup.
For an application-owned OAuth integration, use secret_input_request for a private runtime secret form in remote MCP or secret_set_command for local stdin. Set up Google or GitHub with Better Auth.
Connected chat with remote OAuth
For a client that supports authenticated remote MCP, connect:identity_get, the intended workspace and the requested project before continuing. Current workspace membership, role and any explicit token restrictions determine access. If you already described an application or task, the agent continues it; otherwise it asks what you would like to host.
Existing authenticated connections continue to use their current OAuth identity. If a client has cached older tools or instructions, refresh its catalog or start a fresh chat; a catalog refresh does not require a new OAuth connection. A role or resource denial needs the appropriate current access. An account with no workspace can use workspace_setup and verify identity again afterward.
The client manages its OAuth credential; there is no copied platform token or local device-code login in a connected chat. Verify an authenticated tool call and discover this server’s actual tools. Group private application secret names for one project environment in a single one-hour secret link. The page needs no sign-in and has one field per name, per-field Dice and Copy controls, and one Save. The GitHub source connection uses a protected portal link that lasts ten minutes and needs a portal sign-in as the same user who connected the chat. connection_status reports the status of each link. Runtime secrets describes secret input.
For a complete file tree, the remote tools are source_upload_prepare, source_blob_put, source_upload, source_upload_commit and source_switch. They use actual file contents available to the client; a local directory path gives the chat no filesystem access. Blob uploads return server-computed hash/length receipts. Retain those exact receipts for the complete manifest, and require a succeeded operation plus a committed upload before using its saved SHA. Saving or switching source starts no deployment. Follow the full snapshot and switch flow.
MCP file reads return valid UTF-8 as content_text by default, or base64 when the file cannot be decoded. Remote source_files accepts path and format: "text" | "base64"; local source_file provides the corresponding file read. source_changes accepts exactly one content_text or content_base64 per change, with null base64 for deletion. Follow the returned schemas and preserve the file’s executable flag and source revision guards.
Discover API capabilities in a connected chat
The ChatGPT and Claude directory packages and other authenticated remote clients use the samehttps://app.ohmyho.st/mcp connection. The server offers the same named tool catalog to every client. A client may show the tools approved for its directory listing.
Workspace owners can read usage, remaining credits and current plan with organization_usage_get, organization_credits_get and organization_account_get. Each call checks the user’s current workspace rights and token restrictions. When asked where it is running, the agent can report Agent_Service=codex, Agent_Service=chatgpt, Agent_Service=claude or Agent_Service=unknown. This advisory report carries no permission.
Ask the agent to inspect its actual named tools. The read-only api_reference tool can look up an operation or search a topic, for example query: "database" with limit: 10. It returns bounded API summaries or schemas, the compiled contract hash, the corresponding tool names or support limitation, and links to the complete API reference.
The Master Tool Contract accounts for every public API operation. Its reference lookup cannot execute a request, and a documented operation may require a protected handoff or a separately selected local workflow. Follow the current host’s tool schemas. For database changes, select Dev or Prod explicitly, keep the original idempotency key after uncertainty and inspect the operation/receipt state before reporting success.
A new or changed tool can reach a native host after its checks finish; deploying the server does not prove that the tool is already visible there. Refresh the catalog or start a fresh chat when necessary, preserving the existing OAuth identity. Changes to imported Skills or listing text follow their own package-review process. Local password-file exports, local directory reads and raw credential delivery do not become remote capabilities through API documentation. Secret-bearing webhook creation/activation and mail-webhook preparation/rotation remain documented local/direct REST or existing protected-custody workflows; no new remote secret-input or secret-return channel is added.
Install and sign in locally
Requires Node.js 22 or newer.@amerged/ohmyhost-cli and @amerged/ohmyhost-mcp. Both sources install the ohmyhost and ohmyhost-mcp commands, so keep one source per computer and upgrade from the one already installed (npm ls --global names it). To switch, first remove the other pair: npm uninstall --global @ohmyhost/product-cli @ohmyhost/mcp for the archives, npm uninstall --global @amerged/ohmyhost-cli @amerged/ohmyhost-mcp for npm.
Release manifest and checksums · Current release
The local stdio MCP server uses OHMYHOST_TOKEN when that variable is set in the server process, and otherwise the logins saved by ohmyhost login. With several, pass profile_name per call (profile_list shows names) or bind the server to OHMYHOST_PROFILE=NAME; another requested profile fails profile_context_mismatch. A login added later works on the next call without restarting. A token on its own is enough — no login and no browser. Put it in the same env block as OHMYHOST_ENVIRONMENT; the server reads no .env file and never calls the CLI.
With a token, every tool works except organization_create, organization_list, organization_use, token_create, tokens_list and token_revoke. Those need an interactive login: run the matching ohmyhost command in a shell without OHMYHOST_TOKEN.
After installing or upgrading the clients, restart the MCP server. A running server keeps the tool list it started with, so newly published tools stay invisible until it restarts.
Keep existing servers, models and permission settings. If a server named ohmyho is already configured, inspect it before changing that entry. An old npx configuration pinning a versioned release URL stops when that archive is superseded; use the installed ohmyhost-mcp command. Preserve harness approval policy; rejected mutations are not platform failures, and switching transport cannot bypass approval.
The server’s source is published with every release at amerged-org/ohmyhost-mcp, every file of @amerged/ohmyhost-mcp except its built dist bundle and README, byte for byte. release.json records full-package npm integrity and the SHA-256 of omitted files. For help, ask your agent: it reports through feedback_submit and follows up with feedback_status (Support).
Codex
identity_get and list the available Skills.
Claude Code
/mcp in Claude Code and confirm the connection. Ask it to call identity_get.
Cursor
Merge this server into your existing~/.cursor/mcp.json, or .cursor/mcp.json for this project:
agent mcp list-tools ohmyho. Use your installed CLI’s help if its executable is named differently.
Hermes
OpenClaw
For versions with the native outbound MCP registry:openclaw mcp add --help to confirm support. mcp serve exposes OpenClaw itself and is a different feature. Preserve the current approval policy; a saved registry entry alone does not prove that the running agent has loaded it.
Confirm the connection
Ask the agent: “Read my ohmyho.st identity and list my projects.” It should callidentity_get, then remote project_list or local projects_list, and read project_context_get for the project you select. If a tool is missing, compare the installed client with the current release and reconnect after updating.
These harness commands and the downloadable MCP configuration set up the local ohmyhost-mcp stdio server, with its CLI/device-login profiles and private automation-token support. Its published catalog describes that local client. The remote product endpoint above is a separate OAuth connection. Keep the transport your client supports and its existing permission policy. Mintlify’s search MCP answers documentation questions; it cannot deploy or access your account.
Task Skills · Actual tool catalogue · CLI