# `ai.peerfoundry/typedpull` 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/ai.peerfoundry/typedpull
- JSON: https://anlyon.dev/api/v1/servers/ai.peerfoundry/typedpull
- Version: 0.1.0 (active)
- Publisher: ai.peerfoundry (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-31T11:17:37.989Z

Title and description, as the publisher wrote them:

```untrusted-server-text
TypedPull
Return only the schema fields you name from one public web page. No raw HTML.
```

Scanned 2026-10-31T11:17:51.543Z over streamable-http.

**4 tools: 3 change things and 1 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | 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__typedpull__extract` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__typedpull__explain_extractor` `mcp__typedpull__extract` |

## Findings

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

```untrusted-server-text
The server marks "extract" as not read-only (readOnlyHint: false), and its words say it reads.

annotations: {"readOnlyHint":false,"destructiveHint":false}; The description's first verb is "return": a word for reading.
```


## Changes things (3)

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

### `extract`

- The description's first verb is "return": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
- 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.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Return schema fields from one public page. A miss returns compile_disabled.
```

### `extract_batch`

- The description's first verb is "run": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Run up to 20 extract calls. Each item has its own status.
```

### `keys.create`

- The name "keys.create" says "create": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Mint a pf_ caller key. The raw key is shown once.
```

## Only reads (1)

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

### `explain_extractor`

- The name "explain_extractor" says "explain": a word for reading.
- 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
Show selectors, version, and hit count. This does not fetch the page.
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__typedpull__extract",
      "mcp__typedpull__extract_batch",
      "mcp__typedpull__explain_extractor",
      "mcp__typedpull__keys_create"
    ],
    "deny": []
  }
}
```

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

- `mcp__typedpull__extract`: untrusted-input, outbound
- `mcp__typedpull__explain_extractor`: outbound