# `com.recipeforagents/recipe-for-agents` 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.recipeforagents/recipe-for-agents
- JSON: https://radar.anlyon.com/api/v1/servers/com.recipeforagents/recipe-for-agents
- Version: 1.0.1 (active)
- Publisher: com.recipeforagents (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-11-14T13:17:38.760Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Recipe for Agents
Find the Apify Actor, n8n recipe or agent skill for a web-data job, with ready MCP configs.
```

Scanned 2026-11-14T13:18:17.329Z over streamable-http.

**8 tools: 2 change things and 6 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 2 | ask |
| Only reads | read | 6 | allow |

## Exfil surface

No private-data -> untrusted-input -> outbound path in this server alone: no tool is tagged outbound.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | `mcp__recipe-for-agents__find_recipe` `mcp__recipe-for-agents__get_tool` |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__recipe-for-agents__find_recipe` `mcp__recipe-for-agents__get_tool` `mcp__recipe-for-agents__list_categories` `mcp__recipe-for-agents__list_websites` `mcp__recipe-for-agents__search_tools` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | none |

## Findings

No check matched anything in these tool definitions.


## Changes things (2)

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

### `build_mcp_config`

- 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.

Description, as the server wrote it:

```untrusted-server-text
Ready-to-paste config that adds chosen Actors (or a website's bundle) to an MCP client through Apify's hosted MCP server: Claude Code, Claude Desktop, Cursor, VS Code, ChatGPT, Codex CLI, Gemini CLI or n8n AI Agent, with steps.
```

### `troubleshoot`

- 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.

Description, as the server wrote it:

```untrusted-server-text
Sourced fixes for errors when connecting Apify Actors to Claude, Cursor, VS Code, ChatGPT, Codex, Gemini CLI or n8n (401 unauthorized, 408 timeouts, 429, SSE endpoint gone, tools missing, result too large...).
```

## Only reads (6)

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

### `find_recipe`

- The name "find_recipe" says "find": a word for reading.
- Tag private-data: The description's first sentence says "find" and "email": it reads mail.
- Tag untrusted-input: The description's first sentence says "find" and "web": it reads web pages, which anyone can write.

Description, as the server wrote it:

```untrusted-server-text
Find step-by-step n8n recipes that move live web data into a destination (Google Sheets, Slack, Notion, HubSpot, email, Discord, webhook, Qdrant) for a task such as 'new Zillow listings to Slack', plus matching use cases and agent skills. Suggests Actors when no recipe fits.
```

### `get_recipe`

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

Description, as the server wrote it:

```untrusted-server-text
One recipe in full: what it does, the Actor and input it sends, schedule, de-duplication, setup steps, known limits and, with include_workflow=true, the importable n8n workflow JSON (built-in nodes only).
```

### `get_tool`

- The name "get_tool" says "get": a word for reading.
- Tag private-data: The description's first sentence says "file": it reads files.
- Tag untrusted-input: The description's first sentence says "url": it reads web pages, which anyone can write.

Description, as the server wrote it:

```untrusted-server-text
Everything published about one catalogue Actor: description, price, required and example input, output fields, MCP URL, configs for Claude Code/Cursor/VS Code/Codex, n8n workflow, SKILL.md and schema files, matching recipes.
```

### `list_categories`

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

Description, as the server wrote it:

```untrusted-server-text
The catalogue's categories (leads, social, video, products, property, jobs, search, travel, developer utilities) with Actor counts and the main websites in each.
```

### `list_websites`

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

Description, as the server wrote it:

```untrusted-server-text
Websites the catalogue covers, with the number of Actors for each, its page and one MCP URL bundling its main Actors. Filter by part of the name or by category.
```

### `search_tools`

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

Description, as the server wrote it:

```untrusted-server-text
Find Apify Actors (ready-made scrapers and data tools) an agent can call for a kind of web data, e.g. 'LinkedIn company headcount', 'Amazon prices', 'Google Maps leads with email'. Returns the best matches with website, price, output fields, required input, page and scoped MCP URL. Filter by website or category.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `recipe-for-agents`:

```json
{
  "permissions": {
    "allow": [
      "mcp__recipe-for-agents__search_tools",
      "mcp__recipe-for-agents__get_tool",
      "mcp__recipe-for-agents__find_recipe",
      "mcp__recipe-for-agents__get_recipe",
      "mcp__recipe-for-agents__list_categories",
      "mcp__recipe-for-agents__list_websites"
    ],
    "ask": [
      "mcp__recipe-for-agents__build_mcp_config",
      "mcp__recipe-for-agents__troubleshoot"
    ],
    "deny": []
  }
}
```

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

- `mcp__recipe-for-agents__search_tools`: untrusted-input
- `mcp__recipe-for-agents__get_tool`: private-data, untrusted-input
- `mcp__recipe-for-agents__find_recipe`: private-data, untrusted-input
- `mcp__recipe-for-agents__list_categories`: untrusted-input
- `mcp__recipe-for-agents__list_websites`: untrusted-input

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-21T19:20:54.850Z, unchanged since 2026-11-14T12:19:02.183Z. 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 | `2` |
| 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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

https://recipeforagents.com/mcp-server: tools/list returned 8 tools to an anonymous client, including build_mcp_config (write), troubleshoot (write)
```
