# `page.aft/mcp` on anlyon.dev

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by anlyon.dev. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://anlyon.dev/servers/page.aft/mcp
- JSON: https://anlyon.dev/api/v1/servers/page.aft/mcp
- Version: 1.0.0 (active)
- Publisher: page.aft (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/vaibhavmule/aft.page
- Metadata from the official MCP Registry, synced 2026-10-21T18:54:25.192Z

Title and description, as the publisher wrote them:

```untrusted-server-text
aft.page
Deploy HTML or dist/ to a live HTTPS URL. No account. Drop, MCP, or CLI.
```

Scanned 2026-10-21T19:15:23.800Z over streamable-http.

**6 tools: 1 can delete or cancel things, 1 do something that can't be undone, 3 change things and 1 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 1 | deny |
| Can't be undone | irreversible | 1 | ask |
| Changes things | write | 3 | ask |
| Only reads | read | 1 | allow |

## Exfil surface

No private-data -> untrusted-input -> outbound path in this server alone: no tool is tagged private-data.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | none |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__aft__aft_promote` `mcp__aft__aft_rollback` `mcp__aft__deploy` `mcp__aft__deploy_repo` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__aft__deploy_repo` |

## Findings

- **warn** Annotations that disagree with the tool in `aft_deploys` ([annotation-conflict](https://anlyon.dev/methodology#annotation-conflict))

```untrusted-server-text
The server marks "aft_deploys" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "aft_deploys" says "deploy": a word for a change.
```


## Deletes or cancels (1)

Removes, cancels or revokes something. Claude Code: deny.

### `aft_rollback`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Point the live slug at a prior version from aft_deploys, by version number or deploy_id. Same URL. Needs edit_token from .aft/state.json. Claim not required.
```

## Can't be undone (1)

Sends, pays, publishes or merges: once done, it cannot be taken back. Claude Code: ask.

### `deploy`

- The name "deploy" says "deploy": a word for a change.
- The description's first verb is "publish": a word for a change that another call does not undo.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Publish to a live URL. Pass html (one page) OR files (a built site, or a small app's source). Plain HTML → html. Vite/React → npm run build, then files from dist/. Next static export → files from out/; a static site needs index.html. Flask/FastAPI/Django/Express → the source files with requirements.txt or package.json; aft builds and runs it. Never upload node_modules, .venv, or .next/. First hit: preferred_slug from aft.json (include aft.json in files). Later: same slug + edit_token from .aft/state.json — every update is a new version (v1, v2…) at the same URL. Pass hold:true to keep an update as a preview until aft_promote. label names the version. Limits: 500 files, 25MB each, 100MB total.
```

## Changes things (3)

Creates or changes something that can be changed back. Claude Code: ask.

### `aft_deploys`

- The name "aft_deploys" says "deploy": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
List the versions (v1, v2…) of a slug with their label, door, commit and whether each is live or a held preview. Needs edit_token from .aft/state.json (or the first deploy). Same history the project UI shows after claim.
```

### `aft_promote`

- Nothing in its name or description says what it does, so it is counted as a write.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Make a held preview version live at the same URL. Pass version (e.g. 4) or deploy_id from aft_deploys. Needs edit_token.
```

### `deploy_repo`

- The name "deploy_repo" says "deploy": a word for a change.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

Description, as the server wrote it:

```untrusted-server-text
Same engine as aft.page/run: public GitHub URL → detect → build → live URL. Static is instant; Vite and Next.js build in the background (polls until live or failed). Private repos are refused. For a local project dir, use hosted CLI aft deploy instead.
```

## Only reads (1)

Looks things up and changes nothing. Claude Code: allow.

### `aft_health`

- The description's first verb is "ping": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Ping the aft.page deploy API.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `aft`:

```json
{
  "permissions": {
    "allow": [
      "mcp__aft__aft_health"
    ],
    "ask": [
      "mcp__aft__deploy",
      "mcp__aft__deploy_repo",
      "mcp__aft__aft_deploys",
      "mcp__aft__aft_promote"
    ],
    "deny": [
      "mcp__aft__aft_rollback"
    ]
  }
}
```

Capability tags behind the rules (a read tagged outbound is asked about):

- `mcp__aft__deploy`: untrusted-input
- `mcp__aft__deploy_repo`: untrusted-input, outbound
- `mcp__aft__aft_rollback`: untrusted-input
- `mcp__aft__aft_promote`: untrusted-input

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-10-22T15:12:27.099Z, unchanged since 2026-10-22T15:12:27.099Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://anlyon.dev/methodology#remote-posture

| Fact | Observed |
| --- | --- |
| Reachable | `yes` |
| HTTP status of an anonymous initialize | `200` |
| tools/list served without credentials | `yes` |
| Tools that change things, listed without credentials | `5` |
| Protocol version | `2025-06-18` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `none` |
| Authorization servers | `none` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `not observed` |
| Client ID metadata documents | `not observed` |

- **high** Tools that change things, listed to anyone ([unauth-remote-writes](https://anlyon.dev/methodology#unauth-remote-writes))

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 5 tools that change things (1 destructive, 1 irreversible, 3 write). Whether a call also works without credentials was not tested: tools are never called.

https://mcp.aft.page/mcp: tools/list returned 6 tools to an anonymous client, including aft_rollback (destructive), deploy (irreversible), deploy_repo (write), aft_deploys (write), aft_promote (write)
```