askyourstack-mcp

# AskYourStack MCP server

**Let Claude, ChatGPT, Cursor or Claude Code manage your own Linux servers, with approvals for anything risky.**

AskYourStack is a hosted, remote MCP server. Install a small agent on your server with one line, add your private AskYourStack MCP address to your AI client, and ask in plain words: set up a raw VPS, install Magento or WordPress, fix a 500 error, take backups, clean up malware, harden the server or move a site to a new one. For SEO it reads Google Search Console, Google Analytics 4, Core Web Vitals, on-page audits and your structured data next to what Googlebot really fetches in your server logs, and fixes the causes on the server.

- Website: https://askyourstack.com
- Docs: https://askyourstack.com/docs
- Security model: https://askyourstack.com/security
- Prompt library: https://askyourstack.com/prompts

> This repository holds the listing and documentation for the AskYourStack MCP server. The service itself is hosted at askyourstack.com; there is nothing to build or run locally.

## How it works

1. **Connect your server.** Sign up free at [askyourstack.com](https://askyourstack.com/login?mode=signup), name your server and paste the one-line install as the Linux user who owns your sites (the agent then manages only that user's sites and files), or as root when it should run the whole server. The agent dials out to askyourstack.com over HTTPS: it opens no port, and no SSH key or password is stored anywhere.
2. **Add AskYourStack to your AI client** with your private MCP address from the dashboard (see below).
3. **Ask.** Your AI looks at the server first, explains its plan, and runs the work through AskYourStack's tools. Anything destructive waits for your approval.

## Connect your AI client

Two ways in:

- **Sign in (OAuth):** clients that support sign-in for remote MCP servers connect to `https://askyourstack.com/mcp`. You sign in to AskYourStack, see which app is asking and allow it. Each app gets its own access, which you can end under Security in the dashboard.
- **Private address:** `https://askyourstack.com/mcp/YOUR-ADDRESS`, from the dashboard, for clients without sign-in. Keep it private, and make a new one in the dashboard if it leaks. The examples below use it.

The tool and playbook catalogue is public at `https://askyourstack.com/mcp/catalog`.

**Claude (claude.ai and Claude Desktop):** Settings, Connectors, Add custom connector. Name it AskYourStack, paste the address and leave the OAuth fields empty. [Guide](https://askyourstack.com/claude)

**Claude Code:**

```bash
claude mcp add --transport http sudowhizzy https://askyourstack.com/mcp/YOUR-ADDRESS
```

[Guide](https://askyourstack.com/claude-code)

**Cursor** (`mcp.json`):

```json
{
  "mcpServers": {
    "sudowhizzy": { "url": "https://askyourstack.com/mcp/YOUR-ADDRESS" }
  }
}
```

[Guide](https://askyourstack.com/cursor)

**ChatGPT:** Settings, Connectors, turn on developer mode, then add a custom connector with your address and no authentication. [Guide](https://askyourstack.com/chatgpt)

Any other client that supports remote MCP servers over streamable HTTP works the same way.

## Tools

| Tool | What it does | Plan |
|---|---|---|
| `overview` | Where everything stands in one call: plan, servers and their sites, open problems and warnings from the monitoring, approvals waiting, connected Google properties, saved notes and recent work | Free |
| `propose_plan` | Ask approval once for a job with several risky steps: the user sees every risky step and approves them together; each then runs once, exactly as listed | Free |
| `wait_for_approval` | After giving the user an approval, plan or change-window link, wait in the same turn until they decide, then carry on without them returning to the chat | Starter |
| `save_note`, `forget_note` | Short notes about a server or the account that the next chat sees in `overview` (never passwords: those are refused) | Free |
| `log_work` | A plain summary of a finished task, for the owner's dashboard and the next chat | Free |
| `list_servers` | The servers on the account: online, safety mode, paused | Free |
| `server_facts` | Distro, CPU, memory, disk, package manager, services, ports, Magento and WordPress installs | Free |
| `get_playbook` | Step-by-step guides for the AI (see Playbooks) | Free |
| `health_report` | Disk and inodes, memory, load, failed services, certificates, security updates, reboot needed, backups (age and rhythm), out-of-memory kills, PHP out of workers, database connection limit; on Pro and Agency also software with a known vulnerability | Free |
| `list_sites` | The sites on the server: Magento 2, OpenMage (Magento 1), WordPress and WooCommerce, PrestaShop, Shopware 6, Drupal, Joomla, OpenCart and Laravel, found from the web server's own configuration (Plesk, CloudPanel, RunCloud, DirectAdmin and plain layouts) and in Docker containers: kind, root, domains, access logs, owner, version, database (passwords never shown), its console | Free |
| `logs` | A log by name (web-error, php, magento, wordpress, database, system, mail, auth, or any file) for a time window, with repeated errors counted once, a sample of each and the latest lines | Free |
| `read_file` | Read a file | Free |
| `run` | Run a shell command as the agent's user (root, or the site's own user); read-only commands on Free | Free / Starter |
| `list_jobs`, `job_output` | Follow background jobs, reading only new output | Free |
| `list_snapshots` | Snapshots on the server | Free |
| `start_job`, `stop_job` | Long commands (installs, composer, imports) in the background, surviving the chat | Starter |
| `write_file` | Create or replace a file, keeping the previous version | Starter |
| `snapshot`, `rollback` | Save folders and databases, write them back; a rollback can itself be undone | Starter |
| `db_query` | One SQL statement with the site's own credentials; reads in a read-only transaction | Starter |
| `magento` | `bin/magento` as the site's owner | Starter |
| `wp` | `wp-cli` as the site's owner | Starter |
| `site_console` | Run a site's own command line tool as its owner, also inside a Docker container: bin/console (Shopware 6, PrestaShop), artisan (Laravel), drush (Drupal), Joomla's cli. Lists run straight away; uninstalling, database resets and arbitrary code need approval | Starter |
| `connected_sites` | Sites connected without a server (a WordPress on any host, through its REST API with an application password, or a WhizzyCommerce shop through the shop's own connector): name, mode, content types | Free |
| `content_list`, `content_get` | Read a connected site's posts, pages, media, categories, tags and other content types | Free |
| `content_save`, `content_upload`, `content_trash`, `content_undo` | Write drafts, edit, upload images, trash and undo on a connected site, inside the mode its owner chose (read-only, drafts only, publish too); what a change replaced is kept 90 days | Starter |
| `whizzy_tools` | What a connected WhizzyCommerce shop lets the AI do right now (the merchant decides per group in their WhizzyCommerce dashboard); search for one capability to read its whole input schema | Free |
| `whizzy_call` | Run one capability of a connected WhizzyCommerce shop. Reads answer at once; a change comes back as a preview with a link the merchant confirms in their own dashboard, and its outcome can be read afterwards. Nothing the shop answers is stored | Free (reads), Starter |
| `keyword_volume` | Google search volume, 12-month history, CPC and competition for up to 200 keywords in a country and language (metered: a monthly allowance per plan) | Starter, SEO Starter |
| `keyword_ideas` | Up to 100 keyword suggestions around a seed, with volume, keyword difficulty and intent | Starter, SEO Starter |
| `serp_check` | The live Google results for a keyword, desktop or mobile, with the user's site marked and the page features (AI overview, snippets, people also ask) | Starter, SEO Starter |
| `domain_keywords` | What a domain ranks for, with position, volume, estimated visits and page, and its competitors | Starter, SEO Starter |
| `bing_sites` | The sites in the user's Bing Webmaster Tools account (connected on the SEO page by signing in at Bing or with an API key) and which the AI may read | Starter, SEO Starter |
| `bing_performance` | Bing search performance: daily impressions and clicks, the last 28 days against the 28 before, top queries and pages, the pages of one query or the queries of one page | Starter, SEO Starter |
| `bing_crawl` | Bingbot's crawl: pages crawled and in the index, errors, crawl issues per address, one address inspected | Starter, SEO Starter |
| `bing_keywords` | Keyword research from Bing's own data: searches on Bing for a keyword, monthly history, related keywords | Starter, SEO Starter |
| `bing_backlinks` | Inbound links Bing knows: the site's pages with the most links, and who links to one page with which anchor text | Starter, SEO Starter |
| `bing_sitemaps` | The sitemaps Bing knows for a site with status and counts | Starter, SEO Starter |
| `bing_submit` | Submit up to 500 pages or a sitemap to Bing, with the quota left | Starter, SEO Starter |
| `disavow_file` | The disavow file for Google's disavow links tool, from the user's backlink data (Ahrefs, Semrush, SE Ranking, Bing), merged with the file Google already has and checked against Google's format and limits; the user uploads it (Google has no API for it) | Starter, SEO Starter |
| `cf_zones` | The Cloudflare zones the user connected with an API token (Sites page), with status, plan, name servers and the connection's mode | Starter |
| `cf_dns_list` | List the DNS records of a Cloudflare zone, filtered by type, name or search (part of a name or content), each with its id. | Starter |
| `cf_dns_add` | Add a DNS record to a Cloudflare zone: a new subdomain, a mail record or a verification text. | Starter |
| `cf_dns_change` | Change one DNS record of a Cloudflare zone,