VibeHost MCP Server

VibeHost is a deployment platform built for coding agents. The Model Context Protocol (MCP) server lets a connected AI agent deploy your sites, manage releases, and inspect logs through 61 tools. It works with Claude Desktop, ChatGPT, Gemini Spark, Cursor, Claude Code, Codex, Windsurf, and others.

What it does

VibeHost ships a remote MCP server that any MCP-compatible agent can connect to. Once authorised, the agent can create apps, push deployments (tarball over signed URL), promote between channels, roll back, manage custom domains and redirects, stream container logs, gate apps with passwords or share links, and grant per-app or per-team access. Every action runs through the same OAuth-bound permissions the dashboard uses. Agents only see what the signing user can see.

Endpoints

• MCP server: https://api.vibehost.com/mcp, over the Streamable HTTP transport (the spec's recommended transport since 2025-06).
• OAuth 2.1 authorization server metadata: https://api.vibehost.com/.well-known/oauth-authorization-server (RFC 8414).
• Protected resource metadata: https://api.vibehost.com/.well-known/oauth-protected-resource/mcp (RFC 9728).
• Dynamic client registration: https://api.vibehost.com/api/v1/oauth/register (RFC 7591). New agents register themselves the first time they connect.

Authentication

OAuth 2.1 authorization-code flow with mandatory PKCE (S256). Agents request the mcp scope, plus offline_access if they need a refresh token. Access tokens are 60 minutes; refresh tokens are 30 days with single-use rotation and reuse detection (if the same refresh token is used twice, the entire chain for that client is revoked). Token audience is bound to https://api.vibehost.com/mcp via RFC 8707, so a token minted for VibeHost won't be accepted by another resource server.

Public clients (Claude Desktop, Cursor, ChatGPT, Gemini Spark, Codex, Windsurf, Raycast, Continue, Devin, VS Code, and similar native agents) authenticate via dynamic client registration and PKCE, so they need no client secret. The accepted redirect-URI schemes are: https://, loopback http://localhost and http://127.0.0.1, plus a fixed set of native-agent custom schemes (claude-desktop:, cursor:, vscode:, windsurf:, raycast:, gemini:, continue:, devin:, claude:, claude-code:, codium: ). Confidential clients with a static client_id/secret pair are supported for server-to-server integrations; contact us to provision one.

What your agent can do

The 61 tools split into 8 surfaces. Read-only tools are marked with (read); tools that change publicly visible internet state (deploys, public URLs, custom domains, password gates) carry openWorldHint: true so the client can prompt for confirmation.

Workspaces & apps

• list_workspaces (read) lists the workspaces the OAuth token can reach.
• list_apps (read) and get_app (read) return apps and their metadata.
• create_app provisions a new app (private by default), and delete_app soft-deletes one.
• set_app_visibility sets an app to public, workspace, or private.

Deploys & releases

• check_blobs_missing (read) and request_upload handle the chunked tarball upload through signed R2 URLs.
• deploy promotes a manifest to a channel. Returns the deployment with its status; a static deploy is usually already healthy. Poll get_deployment only while it is starting.
• get_deployment (read) inspects a release, and get_logs (read) returns container logs.
• request_deployment_download (read) returns a signed URL to re-download a deployment's tarball. It powers vibehost pull.
• get_screenshot (read) returns the preview image the previewer worker captures on each healthy deploy.

Channels

• list_channels (read), create_channel.
• promote takes an existing deployment in one channel and points another channel at the same release bytes (no rebuild). Typical flow: deploy to a preview channel, verify, then promote to production.
• rollback works within a single channel and re-points it at one of that channel's earlier deployments.

Access & sharing

• list_app_grants (read) shows who has access, by team or by email.
• grant_app_email_access, revoke_app_email_access, grant_app_team_access, and revoke_app_team_access grant or revoke viewer, deployer, or admin access per recipient.
• get_app_password_info (read), set_app_password, and clear_app_password manage a shared password gate on top of visibility.
• list_share_links (read), create_share_link, and revoke_share_link manage anonymous tokenised URLs with an optional TTL.

Custom domains

• list_custom_domains (read), add_custom_domain, verify_custom_domain, remove_custom_domain.
• verify_custom_domain queries public DNS resolvers for your CNAME / TXT records. add_custom_domain and remove_custom_domain change VibeHost's view of the domain. list_custom_domains is read-only.

Redirects

• list_redirect_rules (read), add_redirect_rule, remove_redirect_rule, and bulk_import_redirect_rules manage per-app redirect and rewrite rules, which Cloudflare Workers serve.

Team & workspace management

• list_workspace_members (read), remove_workspace_member.
• list_team_members (read), remove_team_member.
• list_workspace_invitations (read), invite_to_workspace, revoke_workspace_invitation.
• list_team_invitations (read), invite_to_team, revoke_team_invitation. Invitation emails are sent via Resend.

Example agent prompts

Once your agent is connected to https://api.vibehost.com/mcp, these prompts work as written. The agent calls multiple tools in sequence; you usually don't pick tool names manually.

• "Deploy the contents of ./dist to a new VibeHost app called landing-v2 and give me the URL."
  → create_app → check_blobs_missing → request_upload → deploy → get_deployment.
• "Share landing-v2 with bob@example.com as a deployer."
  → get_app → grant_app_email_access. (Email grants persist until revoked; for time-bounded access use create_share_link with a TTL instead.)
• "Roll landing-v2 production back to the previous release."
  → list_channels + get_deployment → rollback.
• "Add the custom domain landing.example.com to landing-v2 and tell me what CNAME I need to set."
  → add_custom_domain → verify_custom_domain (returns the expected CNAME and TXT records).
• "Show me the last 50 log lines from landing-v2 's current production deployment."
  → list_channels → get_deployment → get_logs.

Read / write capabilities

The server both reads and writes. Of the 61 tools, 22 are strictly read-only (everything prefixed list_, get_, check_); the remaining 39 write or change state. The write tools are annotated with destructiveHint (delete / revoke / clear) and openWorldHint (for changes to publicly visible internet state, such as deploys, share links, custom domains, and password gates) so MCP clients can surface a confirmation prompt before calling.

Data & privacy

VibeHost's privacy policy also applies to access through MCP. The MCP server stores no additional data: every tool call is authenticated against the same user / token DB rows the dashboard uses, every state change is audit-logged the same way, and OAuth refresh tokens are hashed at rest. Tools that touch third-party services (invitation emails via Resend; DNS lookups against public resolvers for verify_custom_domain) declare openWorldHint: true so clients can warn users.

Support

• Support: contact@vibehost.com
• Privacy concerns: contact@vibehost.com

Last updated: 2026-05-13.