# `io.github.seotrader/speedcontent-social` 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/io.github.seotrader/speedcontent-social
- JSON: https://radar.anlyon.com/api/v1/servers/io.github.seotrader/speedcontent-social
- Version: 0.1.1 (active)
- Publisher: io.github.seotrader (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/seotrader/speedcontent-social-mcp
- Metadata from the official MCP Registry, synced 2026-10-21T18:49:10.168Z

Title and description, as the publisher wrote them:

```untrusted-server-text
SpeedContent Social
Generate platform-native social posts that are humanized, AI-detection scored and illustrated.
```

Scanned 2026-11-20T12:17:39.957Z over streamable-http.

**5 tools: 4 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 | 4 | 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__speedcontent-social__check_social_job` `mcp__speedcontent-social__generate_social_post` `mcp__speedcontent-social__humanize_text` `mcp__speedcontent-social__list_social_platforms` `mcp__speedcontent-social__score_text` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__speedcontent-social__generate_social_post` |

## Findings

No check matched anything in these tool definitions.


## Changes things (4)

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

### `check_social_job`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- 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
Look up a social post generation job by id. Returns the finished posts once the job completes, or its current progress while it runs. Costs nothing.
```

### `generate_social_post`

- The name "generate_social_post" says "generate": 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 name "generate_social_post" says "generate" and "post": it writes something other people read.

Description, as the server wrote it:

```untrusted-server-text
Write a social media post from scratch for a given platform and topic. Use this when you do not already have a draft — for example to produce several variations at once, or for platforms whose conventions you are unsure of. If you have already written the post yourself, prefer score_text and humanize_text, which check and fix your own wording instead of replacing it. Returns a job id immediately — poll it with check_social_job, which usually completes in 20-90 seconds. Costs credits.
```

### `humanize_text`

- 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
Rewrite text so it no longer reads as machine-written, using an external humanizing service. Use this on your own writing when score_text says it would be flagged. Brand names, domains and any lines listed in `preserve` are restored verbatim afterwards, because the humanizer rewrites whole sentences and splits names. Costs 1 credit per 20 words.
```

### `score_text`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- 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
Check how machine-written a piece of text reads, using an external AI detector. Returns a score from 0 to 65 where 0 reads as human and anything above 30 is likely to be flagged. Use this on text you have already written to find out whether it will pass before it is published — it is a measurement you cannot make yourself. Costs 8 credits per call.
```

## Only reads (1)

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

### `list_social_platforms`

- The name "list_social_platforms" says "list": a word for reading.
- Tag untrusted-input: The description's first sentence says "list" and "post": it reads posts, which other people can write.

Description, as the server wrote it:

```untrusted-server-text
List the platforms generate_social_post supports, with each one's default post length and emoji policy. Costs nothing and makes no network call.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `speedcontent-social`:

```json
{
  "permissions": {
    "allow": [
      "mcp__speedcontent-social__list_social_platforms"
    ],
    "ask": [
      "mcp__speedcontent-social__generate_social_post",
      "mcp__speedcontent-social__score_text",
      "mcp__speedcontent-social__humanize_text",
      "mcp__speedcontent-social__check_social_job"
    ],
    "deny": []
  }
}
```

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

- `mcp__speedcontent-social__generate_social_post`: untrusted-input, outbound
- `mcp__speedcontent-social__score_text`: untrusted-input
- `mcp__speedcontent-social__humanize_text`: untrusted-input
- `mcp__speedcontent-social__check_social_job`: untrusted-input
- `mcp__speedcontent-social__list_social_platforms`: untrusted-input

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T19:10:51.117Z, unchanged since 2026-11-13T12:09:21.780Z. 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` |

- **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 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.

https://speedcontent.online/mcp: tools/list returned 5 tools to an anonymous client, including generate_social_post (write), score_text (write), humanize_text (write), check_social_job (write)
```

Posture changes:

- 2026-11-13T12:09:21.780Z: Reachable `no` -> `yes`; HTTP status of an anonymous initialize `none` -> `200`; tools/list served without credentials `no` -> `yes`; Tools that change things, listed without credentials `0` -> `4`; Protocol version `none` -> `2025-06-18`
- 2026-11-06T05:08:12.008Z: Reachable `yes` -> `no`; HTTP status of an anonymous initialize `200` -> `none`; tools/list served without credentials `yes` -> `no`; Tools that change things, listed without credentials `4` -> `0`; Protocol version `2025-06-18` -> `none`
