# `com.synairo.api/autopay` on Anlyon Radar

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by Anlyon Radar. 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://radar.anlyon.com/servers/com.synairo.api/autopay
- JSON: https://radar.anlyon.com/api/v1/servers/com.synairo.api/autopay
- Version: 1.6.0 (active)
- Publisher: com.synairo.api (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-11-20T09:17:40.388Z

Title and description, as the publisher wrote them:

```untrusted-server-text
AutoPay
Paid tools for agents: search, verify, web-to-Markdown, PDF extraction, security scans. x402 USDC
```

Scanned 2026-11-20T09:18:00.202Z over streamable-http.

**13 tools: 10 change things and 3 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 10 | ask |
| Only reads | read | 3 | 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__autopay__fetch` `mcp__autopay__search` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__autopay__extract` `mcp__autopay__fetch` `mcp__autopay__security_scan` `mcp__autopay__security_scan_dns` `mcp__autopay__security_scan_exposure` `mcp__autopay__security_scan_full` `mcp__autopay__security_scan_headers` `mcp__autopay__security_scan_tls` |

## Findings

- **high** References to secrets on disk in `security_scan` ([sensitive-path](https://radar.anlyon.com/methodology#sensitive-path))

```untrusted-server-text
The description refers to ".git/.env/server-status/directory".

description: "...ers, SPF/DMARC/DKIM/CAA/DNSSEC, exposed .git/.env/server-status/directory listing, security.txt; score + grade. $..."
```

- **high** References to secrets on disk in `security_scan_exposure` ([sensitive-path](https://radar.anlyon.com/methodology#sensitive-path))

```untrusted-server-text
The description refers to "/.env".

description: "...sive only): single GETs for /.git/HEAD, /.env, /server-status, directory listing, sec..."
```


## Changes things (10)

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

### `extract`

- Nothing in its name or description says what it does, so it is counted as a write.
- 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
Document extraction: PDF/image (url or file_base64, max 10 MB) -> typed fields, line items, OCR text, document type ($0.025 per page, max 5 pages billed; synchronous, charged only on success). Pay with X-PAYMENT (x402 USDC on Base) or a prepaid API key.
```

### `research`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Queue a short cited brief ($0.30). Pay with X-PAYMENT (x402 USDC on Base) or a prepaid API key. Returns 202 with job_id. Typical ETA 10–20 minutes; poll get_job.
```

### `security_scan`

- Nothing in its name or description says what it does, so it is counted as a write.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
- Findings: high sensitive-path

Description, as the server wrote it:

```untrusted-server-text
Quick passive security scan (passive only): TLS/cert, HTTPS redirect, HSTS + security headers, SPF/DMARC/DKIM/CAA/DNSSEC, exposed .git/.env/server-status/directory listing, security.txt; score + grade. $0.01; synchronous, charged only on success. Pay with X-PAYMENT (x402 USDC on Base) or a prepaid API key.
```

### `security_scan_dns`

- Nothing in its name or description says what it does, so it is counted as a write.
- 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
DNS / e-mail security check (passive only): SPF, DMARC, DKIM (common selectors), MX, CAA, DNSSEC; score + grade. $0.003; synchronous, charged only on success. Pay with X-PAYMENT (x402 USDC on Base) or a prepaid API key.
```

### `security_scan_exposure`

- Nothing in its name or description says what it does, so it is counted as a write.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
- Findings: high sensitive-path

Description, as the server wrote it:

```untrusted-server-text
Exposed files check (passive only): single GETs for /.git/HEAD, /.env, /server-status, directory listing, security.txt; score + grade. $0.005; synchronous, charged only on success. Pay with X-PAYMENT (x402 USDC on Base) or a prepaid API key.
```

### `security_scan_full`

- Nothing in its name or description says what it does, so it is counted as a write.
- 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
Full passive security review (passive only): everything in quick + cookie flags, mixed content, server/version disclosure, RDAP domain age/expiry, up to 5 same-site subpages, prioritized step-by-step remediation plan. $0.99; synchronous, charged only on success. Pay with X-PAYMENT (x402 USDC on Base) or a prepaid API key.
```

### `security_scan_headers`

- Nothing in its name or description says what it does, so it is counted as a write.
- 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
Security headers check (passive only): HTTPS redirect, HSTS, CSP, X-Frame-Options/frame-ancestors, X-Content-Type-Options, Referrer-Policy, Permissions-Policy; score + grade. $0.003; synchronous, charged only on success. Pay with X-PAYMENT (x402 USDC on Base) or a prepaid API key.
```

### `security_scan_tls`

- Nothing in its name or description says what it does, so it is counted as a write.
- 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
TLS certificate check (passive only): certificate trust, issuer, SAN, expiry, negotiated TLS version; score + grade. $0.002; synchronous, charged only on success. Pay with X-PAYMENT (x402 USDC on Base) or a prepaid API key.
```

### `verify`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Queue a claim/company/URL verification ($0.08). Pay with X-PAYMENT (x402 USDC on Base) or a prepaid API key. Returns 202 with job_id. Typical ETA 10–20 minutes; poll get_job.
```

### `wallet`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Base wallet snapshot: ETH and USDC balance, nonce, contract check, optional ERC-20 balance ($0.01, synchronous, charged only on success). Pay with X-PAYMENT (x402 USDC on Base) or a prepaid API key.
```

## Only reads (3)

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

### `fetch`

- The name "fetch" says "fetch": a word for reading.
- Tag untrusted-input: The description's first sentence says "fetch" and "web": it reads web pages, which anyone can write. The input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
- Claude Code: ask, because it is tagged outbound.

Description, as the server wrote it:

```untrusted-server-text
Fetch one public web page and return clean Markdown ($0.01, synchronous, charged only on success). Pay with X-PAYMENT (x402 USDC on Base) or a prepaid API key.
```

### `get_job`

- The name "get_job" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Poll a previously queued AutoPay job by id until status is done.
```

### `search`

- The name "search" says "search": a word for reading.
- Tag untrusted-input: The description's first sentence says "web": it reads web pages, which anyone can write.

Description, as the server wrote it:

```untrusted-server-text
Queue a cited web lookup ($0.01). Pay with X-PAYMENT (x402 USDC on Base) or a prepaid API key. Returns 202 with job_id. Typical ETA 10–20 minutes; poll get_job.
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__autopay__search",
      "mcp__autopay__get_job"
    ],
    "ask": [
      "mcp__autopay__verify",
      "mcp__autopay__research",
      "mcp__autopay__fetch",
      "mcp__autopay__wallet",
      "mcp__autopay__extract",
      "mcp__autopay__security_scan",
      "mcp__autopay__security_scan_headers",
      "mcp__autopay__security_scan_tls",
      "mcp__autopay__security_scan_dns",
      "mcp__autopay__security_scan_exposure",
      "mcp__autopay__security_scan_full"
    ],
    "deny": []
  }
}
```

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

- `mcp__autopay__search`: untrusted-input
- `mcp__autopay__fetch`: untrusted-input, outbound
- `mcp__autopay__extract`: outbound
- `mcp__autopay__security_scan`: outbound
- `mcp__autopay__security_scan_headers`: outbound
- `mcp__autopay__security_scan_tls`: outbound
- `mcp__autopay__security_scan_dns`: outbound
- `mcp__autopay__security_scan_exposure`: outbound
- `mcp__autopay__security_scan_full`: outbound

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T18:19:19.125Z, unchanged since 2026-11-20T18:19:19.125Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://radar.anlyon.com/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 | `12` |
| Protocol version | `2024-11-05` |
| 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` |

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

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 12 tools that change things (12 write). Whether a call also works without credentials was not tested: tools are never called.

https://api.synairo.com/mcp: tools/list returned 21 tools to an anonymous client, including wallet (write), email_check (write), verify (write), research (write), extract (write) and 7 more
```
