# scrape_knowledge_url

Fetch a URL's content into the knowledge base. Server crawls the URL, stores the response body in R2, returns the new document ID. Failures store the row with status='failed'. Use for adding marketing pages, FAQ docs, or external references the agent should be aware of.

Agent View of the PolicyLayer registry record for `scrape_knowledge_url`. HTML page: https://policylayer.com/tools/io-favcrm-favcrm/scrape-knowledge-url

## Facts

- Tool: `scrape_knowledge_url`
- Server: FavCRM (`https://api.favcrm.io/mcp`) — https://policylayer.com/tools/io-favcrm-favcrm.md
- Homepage: https://github.com/favcrm/mcp
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server CORS policy: *
- Server rate-limited: no
- Parameters: 1 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `url` | string | yes | URL to fetch (must be https / http and publicly reachable) |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "scrape_knowledge_url",
    "arguments": {
      "url": "<url>"
    }
  }
}
```

## Why scrape_knowledge_url is rated Medium

This tool fetches external URL content and writes it into the knowledge base (stored in R2 object storage). It creates a new document record, which is a reversible write operation. The severity is medium because a malicious or erroneous URL could pollute the knowledge base with harmful or misleading content that an AI agent may later rely upon, but the action itself is not irreversible (records can be deleted).

From the tool's own definition: "Fetch a URL's content into the knowledge base... stores the response body in R2, returns the new document ID"

Risk signals: Accepts URL/endpoint input (url)

## Use case

AI agents use scrape_knowledge_url to create or update resources in FavCRM, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FavCRM environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches FavCRM:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "scrape_knowledge_url": {
      "limits": [
        {
          "counter": "scrape_knowledge_url_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on FavCRM (219)

- `cancel_booking` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/cancel-booking.md
- `delete_account` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/delete-account.md
- `delete_campaign` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/delete-campaign.md
- `delete_category` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/delete-category.md
- `delete_contact` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/delete-contact.md
- `delete_custom_field` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/delete-custom-field.md
- `delete_deal` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/delete-deal.md
- `delete_invoice` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/delete-invoice.md
- `delete_knowledge_document` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/delete-knowledge-document.md
- `delete_post` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/delete-post.md
- `delete_post_type` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/delete-post-type.md
- `delete_post_type_field` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/delete-post-type-field.md
- `delete_promotion` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/delete-promotion.md
- `delete_segment` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/delete-segment.md
- `delete_service_package` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/delete-service-package.md
- `delete_tag` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/delete-tag.md
- `delete_task` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/delete-task.md
- `remove_post_block` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/remove-post-block.md
- `void_invoice` — Destructive — https://policylayer.com/tools/io-favcrm-favcrm/void-invoice.md
- `execute_tool` — Execute — https://policylayer.com/tools/io-favcrm-favcrm/execute-tool.md
- `switch_company` — Execute — https://policylayer.com/tools/io-favcrm-favcrm/switch-company.md
- `cancel_subscription` — Financial — https://policylayer.com/tools/io-favcrm-favcrm/cancel-subscription.md
- `create_plan_upgrade_link` — Financial — https://policylayer.com/tools/io-favcrm-favcrm/create-plan-upgrade-link.md
- `create_subscription` — Financial — https://policylayer.com/tools/io-favcrm-favcrm/create-subscription.md
- `enrol_membership` — Financial — https://policylayer.com/tools/io-favcrm-favcrm/enrol-membership.md
- `record_invoice_payment` — Financial — https://policylayer.com/tools/io-favcrm-favcrm/record-invoice-payment.md
- `check_plan_operation` — Read — https://policylayer.com/tools/io-favcrm-favcrm/check-plan-operation.md
- `get_attachment_text` — Read — https://policylayer.com/tools/io-favcrm-favcrm/get-attachment-text.md
- `get_audit_log` — Read — https://policylayer.com/tools/io-favcrm-favcrm/get-audit-log.md
- `get_available_slots` — Read — https://policylayer.com/tools/io-favcrm-favcrm/get-available-slots.md
- …and 189 more: https://policylayer.com/tools/io-favcrm-favcrm.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-favcrm-favcrm · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-favcrm-favcrm