ohmyho.st
Overview
Description from the maker (original English)
Operate ohmyho.st hosting from your coding agent: deploy GitHub apps, Postgres, mail, domains.
PopNx MCP’s three pillars
These three are never merged into one score: opinions, measurements and popularity are different things.
- User voiceiNo reviews yetReviews open together with accounts in a later step
- Our basic checksi2 of 2 passedChecked from public information; code not scanned yet
- UsageiEarly↓ 1.8K/wk · ★ 0
What you can do with it
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
- Connection: Runs on your computer
- Transport: stdio
- Category: Developer tools
- You need to fill in: OHMYHOST_TOKEN
Install
Pick the AI app you use, then copy the settings.
Before you install
- Basic checks: 2 of 2 passed
- Runs on your computer with your user’s permissions (files, network, apps).
- You fill in yourself:
OHMYHOST_ENVIRONMENT,OHMYHOST_TOKEN
Values marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"ohmyhost": {
"command": "npx",
"args": [
"-y",
"@amerged/ohmyhost-mcp"
],
"env": {
"OHMYHOST_ENVIRONMENT": "your-value",
"OHMYHOST_TOKEN": "your-value"
}
}
}
}Run this in your terminal
claude mcp add ohmyhost --env OHMYHOST_ENVIRONMENT=your-value --env OHMYHOST_TOKEN=your-value -- npx -y @amerged/ohmyhost-mcpFill in the empty values before running it.
Or copy the settings yourself
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"ohmyhost": {
"command": "npx",
"args": [
"-y",
"@amerged/ohmyhost-mcp"
],
"env": {
"OHMYHOST_ENVIRONMENT": "your-value",
"OHMYHOST_TOKEN": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Or copy the settings yourself
Paste into .vscode/mcp.json in your project
{
"servers": {
"ohmyhost": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@amerged/ohmyhost-mcp"
],
"env": {
"OHMYHOST_ENVIRONMENT": "your-value",
"OHMYHOST_TOKEN": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
Values you fill in
OHMYHOST_ENVIRONMENTenvPlatform to use: production (default) or development.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Which apps can use it
Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Run on your computer in
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
What it can do
Runs on your computer; the tool list appears in your AI app after you install it.
Basic checksi
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 10, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account amerged-org, which owns the repo
- ✓ Pass
Still maintained
Code last changed yesterday
- … Not checked yet
Has a licence
We have not read this repo from GitHub yet
- – Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
- – Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
- … Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints
Compared with others in Developer toolsi
- More stars than 0% of the other 5729 servers in this category
- Published to the registry more recently than 93% of the other 5729 servers in this category
- Basic checks equal to or better than 100% of the other 5729 servers in this category
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
Common questions
Is ohmyho.st safe?
It passed 2 of 2 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
What keys or codes does it need?
You need to fill in: OHMYHOST_TOKEN
Does it run on my computer or in the cloud?
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
Is it still maintained?
The GitHub repo last changed yesterday, and the latest version (0.1.53) reached the registry yesterday.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
What can I use instead?
In the same category: REA, Netdata, Front-End Checklist
Alternatives
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Netdata
Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Front-End Checklist
Review frontend code and live pages against 386 quality-gated web development rules.
README from the maker
Open the README
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
ohmyho.st MCP server
The local MCP server of ohmyho.st, hosting that a coding agent operates. It runs over stdio next to Codex, Claude Code, Cursor, Hermes or OpenClaw and lets the agent deploy the user's GitHub apps and manage their databases, domains, mail, usage and budgets with the access the user grants. It is also how the agent reaches ohmyho.st support.
Version 0.1.50 · npm · Node.js 22 or newer · release.json
This repository mirrors the source published in the npm package @amerged/ohmyhost-mcp. Every release replaces it from the registry tarball, so pull requests are not merged here; report a problem through your agent (see Support below).
Install
npm install --global @amerged/ohmyhost-cli @amerged/ohmyhost-mcp
export OHMYHOST_ENVIRONMENT=production ohmyhost login --json
Installed the clients from the ohmyho.st release archives before? Remove them first with npm uninstall --global @ohmyhost/product-cli @ohmyhost/mcp: both installs provide the ohmyhost and ohmyhost-mcp commands, and npm stops the second one with EEXIST.
Register it with your agent
| Harness | Register the local server | Confirm in the running harness |
|---|---|---|
| Codex | codex mcp add ohmyho --env OHMYHOST_ENVIRONMENT=production -- ohmyhost-mcp | Reload if requested; call identity_get and read the Skill resources. |
| Claude Code | claude mcp add --transport stdio --scope user --env OHMYHOST_ENVIRONMENT=production ohmyho -- ohmyhost-mcp | Open /mcp, confirm connection and call identity_get. |
| Cursor | Merge the token-free https://ohmyho.st/mcp.json server into the existing global or project MCP config. | Confirm in settings; current CLI supports agent mcp list-tools ohmyho. Resolve installed executable/help. |
| Hermes | hermes mcp add ohmyho --command ohmyhost-mcp --env OHMYHOST_ENVIRONMENT=production | hermes mcp test ohmyho, then reload the agent session. |
| OpenClaw | openclaw mcp add ohmyho --command ohmyhost-mcp --env OHMYHOST_ENVIRONMENT=production where the installed native registry supports it. | openclaw mcp probe ohmyho --json, then verify runtime-visible tools. |
Confirm the connection and call identity_get; a saved configuration alone is not a working connection.
Authenticate
Authenticate one of two ways: load OHMYHOST_TOKEN from a private credential source into the server environment, or sign in with ohmyhost login --json and let MCP use the saved logins. With several saved logins, pass profile_name on each call (profile_list shows the names), or bind the server to one login with OHMYHOST_PROFILE=NAME next to OHMYHOST_ENVIRONMENT; a bound server refuses calls for another login (profile_context_mismatch). A server registered for the user serves every session on this computer, so bind it only when the customer asks, and reload it afterwards. The token wins wherever it is set and needs no browser. New user API tokens are optional and remain valid until revoked; the portal shows a new value once, while CLI/MCP token creation saves it directly to the chosen private env file. Login and token lifetimes are separate.
Keep tokens out of shared or committed MCP configuration; the public configuration carries only OHMYHOST_ENVIRONMENT=production.
Tools
application_domain_identity_authorization_revoke: Revoke the current application identity DNS grant with explicit confirmation.application_domain_identity_authorization_status: Read the selected project application-domain identity DNS authorization status.application_domain_identity_authorize: Request exact-purpose Cloudflare consent to write this project hostname ownership challenge at the current revision.application_domain_identity_declare: Declare the intended customer application hostname before deployment.application_domain_identity_get: Read the project intended application hostname, current revision and ownership proof.application_domain_identity_revoke: Revoke only the selected current application-domain proof with explicit confirmation.application_domain_identity_verify: Verify the exact current project and hostname TXT challenge independently of deployment.billing_checkout_create: Owner-only: create or resume a hosted Checkout.billing_checkout_get: Owner-only: observe the original checkout and reconcile confirmed credits/refunds, without another purchase.billing_portal_create: Owner-only: return a short-lived Stripe portal URL to the human for invoices, payment methods or cancellation at period end.billing_recharge_configure: Owner-only: enable or disable automatic off-session payments.billing_recharge_get: Owner-only: read auto-recharge consent, spending limit and payment handoff.database_access_create: Issue a time-bound PostgreSQL credential for this project's own Dev or Prod database.database_access_list: List this project's issued database credentials with their state (active, expired or revoked).database_access_revoke: Revoke one issued database credential immediately: open sessions end and its PostgreSQL role is removed.database_compute_get: Read current managed database memory, total storage, region and observed state without running SQL or waking the database.database_compute_set: Choose fixed database RAM: 256, 512, 1024, 2048 or 4096 MiB.database_execution_usage_get: Read metered database execution usage: schedule runs and webhook attempts per UTC hour or day window.database_query: Read one owner-authorized Dev or Prod database query (at most 100 rows, five-second timeout).database_schedule_delete: Remove one database schedule so it never runs again.database_schedule_list: List this project's database schedules of one Dev or Prod environment (dev when omitted), with their cadence, statements, timeout and next run.database_schedule_run_list: List the newest runs of one database schedule, newest first, with each run's outcome (succeeded, failed, timed_out, outcome_unknown, rejected or a skipped reason) and SQLSTATE when one applies.database_schedule_run_now: Queue one immediate run of a database schedule.database_schedule_set: Create or replace a named database schedule that runs SQL statements repeatedly on a timer, as the application's own runtime role, so row-level security applies.database_table_create: Create one ordinary table in the public schema of a Dev or Prod database, as the migration role with the same access as migration tables, so a database_watch_create can attach later.database_watch_create: Publish row changes of one table of a Dev or Prod database as data events: only the listed columns (at most 32) of each insert, update or delete are published, with the event type data. returned by this call.database_watch_delete: Remove the capture trigger of one database watch: its table publishes no more data events.database_watch_list: List this project's database watches of one Dev or Prod environment (dev when omitted).database_webhook_create: Subscribe one HTTPS receiver to database lifecycle events (database.created, ready, woke, slept, suspended, resized, deleted) of one Dev or Prod database, or to data events: data. for the rows of one watched table (the event type database_watch_create returns) or data.* for every watched table; a bare * never matches data events.database_webhook_delete: Stop all deliveries to one database webhook.database_webhook_delivery_list: List recent database webhook deliveries, newest first, optionally for one webhook.database_webhook_delivery_replay: Queue one more attempt for a database webhook delivery that is no longer being retried.database_webhook_list: List this project's database webhooks of one Dev or Prod environment (dev when omitted), without signing secrets.database_webhook_test: Send one signed test request to a database webhook and report the outcome synchronously.database_write: Execute one explicitly authorized INSERT, UPDATE or DELETE/upsert in the chosen Dev or Prod database.delete_execute: Execute a reviewed project deletiondelete_plan: Plan complete project deletiondeployment_create: Start a reviewed deployment plandeployment_get: Get one deploymentdeployment_logs: List the newest normalized diagnostics of one deployment (build, control, runtime and function failures with catalog codes).deployment_plan: Plan an immutable deployment.deployments_list: List project deploymentsdomain_cloudflare_authorize: Check domain_cloudflare_status first and reuse a valid matching grant.domain_cloudflare_status: Read the project's customer DNS authorization state, zone, scopes and expiry without credentials.domain_paid_apply: Declare or activate the explicitly requested customer hostname.domain_paid_delete: Delete only the explicitly named project's stored customer hostname/route and owned DNS records.domain_paid_plan: Plan a customer-owned production hostname before or after the first Prod deployment.domain_paid_status: Read DNS/TLS and effective Paid-domain access.feedback_status: Read the status of a feedback receipt you submitted and ohmyho.st's customer-visible replies: received, in_review, planned, in_progress, resolved (the fix is live in the named release) or closed (with an explanation).feedback_submit: Report a bug, suspected issue or feature request to ohmyho.st.function_runs_list: List the newest scheduled function runs (functions.crons) of an environment: one run per due UTC minute with state, attempt, the status the scheduled handler returned and timing.github_connect: Owner or Admin: connect GitHub once for this workspace.github_status: Read this workspace's GitHub connection.identity_get: Get the ohmyho.st customer/agent identity this call acts as: user and account email, scoped organization IDs and names and, in context, the saved login or OHMYHOST_TOKEN that supplied it.mail_binding_detach: Detach only this project send binding with current revision and explicit confirmation.mail_binding_get: Read the Prod sender binding and per-project From addresses, default From and default Reply-To.mail_binding_set: Attach a verified workspace sender or update its project settings.mail_domain_delete: Retire the project's mail domain while the project stays active; use its Prod environment ID.mail_domain_set: Configure the project's one production mail domain using its Prod environment ID.mail_domain_status: Read separate sending and receiving readiness and exact DNS records for the project’s production mail domain.mail_message_get: Read only this project's Prod-received message before the hard 72-hour expiry.mail_message_retry: Retry the Prod customer webhook within its shared budget: initial attempt plus at most three retries, all before 72 hours from receipt.- `mail_mess