# `dev.stitchapi/docs` 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/dev.stitchapi/docs
- JSON: https://radar.anlyon.com/api/v1/servers/dev.stitchapi/docs
- Version: 1.1.0 (active)
- Publisher: dev.stitchapi (domain proven to the MCP Registry)
- Runs: remote (streamable-http), local (npm)
- Sign-in to list tools: none
- Repository: https://github.com/rejifald/StitchAPI
- Metadata from the official MCP Registry, synced 2026-10-21T18:12:20.892Z

Title and description, as the publisher wrote them:

```untrusted-server-text
StitchAPI Docs
Search and read the StitchAPI docs: search_docs finds relevant sections, get_doc reads a page.
```

Scanned 2026-11-11T09:18:24.735Z over streamable-http.

**2 tools: 2 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 0 | ask |
| Only reads | read | 2 | allow |

## Exfil surface

2 private-data -> untrusted-input -> outbound paths in this server alone. Denying 1 outbound tool breaks every one: `mcp__docs__get_doc`.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | `mcp__docs__get_doc` `mcp__docs__search_docs` |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__docs__get_doc` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__docs__get_doc` |

| Private data | Untrusted input | Outbound |
| --- | --- | --- |
| `mcp__docs__get_doc` | `mcp__docs__get_doc` | `mcp__docs__get_doc` |
| `mcp__docs__search_docs` | `mcp__docs__get_doc` | `mcp__docs__get_doc` |

## Findings

No check matched anything in these tool definitions.


## Only reads (2)

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

### `get_doc`

- The name "get_doc" says "get": a word for reading.
- Tag private-data: The name "get_doc" says "get" and "doc": it reads documents. The description's first sentence says "fetch" and "doc": it reads documents.
- Tag untrusted-input: 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 a full StitchAPI documentation page as Markdown — the "read the whole thing" escape hatch for a search_docs hit. Pass a `url` (as returned by search_docs) or a `slug` like "guides/resilience/throttle".
```

### `search_docs`

- The name "search_docs" says "search": a word for reading.
- Tag private-data: The name "search_docs" says "search" and "doc": it reads documents.

Description, as the server wrote it:

```untrusted-server-text
Search the StitchAPI documentation semantically (hybrid BM25 + vector). Returns the most relevant doc sections as excerpts with deep links — never full pages. Follow up with get_doc to read a full page.
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__docs__search_docs"
    ],
    "ask": [
      "mcp__docs__get_doc"
    ],
    "deny": []
  }
}
```

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

- `mcp__docs__search_docs`: private-data
- `mcp__docs__get_doc`: private-data, untrusted-input, outbound

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T18:52:56.145Z, unchanged since 2026-10-22T14:46:48.657Z. 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 | `0` |
| 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` |
