# `com.sapiensolutions/site` 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.sapiensolutions/site
- JSON: https://radar.anlyon.com/api/v1/servers/com.sapiensolutions/site
- Version: 1.1.0 (active)
- Publisher: com.sapiensolutions (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-25T01:17:40.364Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Sapien Solutions
Sapien Solutions, Cleveland: what we build, our work, where we work, and inquiries.
```

Scanned 2026-11-09T03:17:48.196Z over streamable-http.

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

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | 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 or untrusted-input.

| 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. | none |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__site__request_inquiry` |

## Findings

No check matched anything in these tool definitions.


## Can't be undone (1)

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

### `request_inquiry`

- The name "request_inquiry" says "request": a word for a change.
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
- Tag outbound: The input takes a destination (input.phone): what the tool writes goes there.

Description, as the server wrote it:

```untrusted-server-text
Send us an inquiry. It reaches the people who do the work, by email. Needs a name, an email or a phone, and what they need.
```

## Changes things (3)

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

### `case_studies`

- 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
Our anonymized case studies: title, summary and links. Use read_page for the full text.
```

### `company`

- 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
Who we are, the four lines of work, where we work, how an engagement runs, and how to reach us. Call this first.
```

### `service_area`

- 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
Whether we work on site or remotely for a place, per line of work. Give a town, county, state or address.
```

## Only reads (1)

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

### `read_page`

- The name "read_page" says "read": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
The full text of one page of our site as markdown, by its path, such as /how-we-work.
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__site__read_page"
    ],
    "ask": [
      "mcp__site__company",
      "mcp__site__case_studies",
      "mcp__site__service_area",
      "mcp__site__request_inquiry"
    ],
    "deny": []
  }
}
```

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

- `mcp__site__request_inquiry`: outbound

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T18:46:22.212Z, unchanged since 2026-10-22T14:40:05.219Z. 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 | `4` |
| 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://radar.anlyon.com/methodology#unauth-remote-writes))

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 4 tools that change things (1 irreversible, 3 write). Whether a call also works without credentials was not tested: tools are never called.

https://sapiensolutions.com/mcp: tools/list returned 5 tools to an anonymous client, including request_inquiry (irreversible), company (write), case_studies (write), service_area (write)
```
