# PreClick — An MCP-native URL preflight scanning service for autonomous agents (formerly URLCheck). (slim)

> PreClick — An MCP-native URL preflight… (ai.urlcheck/urlcheck-mcp), an MCP server by urlcheck.ai, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. PreClick scans links for threats and confirms intent match with high…

- Full: https://www.anchorterminal.com/tools/urlcheck-mcp.md (~950 tokens) · this version ~880 tokens · JSON https://www.anchorterminal.com/tools/urlcheck-mcp.json · canonical https://www.anchorterminal.com/tools/urlcheck-mcp
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05

# PreClick — An MCP-native URL preflight scanning service for autonomous agents (formerly URLCheck).

> Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/

- Kind: MCP server, by urlcheck.ai (https://preclick.ai)
- Category: Travel & booking (https://www.anchorterminal.com/categories/travel.md)
- Listed because: It's published in the registry under urlcheck.ai, a namespace the registry only gives to whoever proves they control that domain.
- What the official MCP registry says: PreClick scans links for threats and confirms intent match with high accuracy before agents click.

## Facts

- MCP registry: `ai.urlcheck/urlcheck-mcp` 0.1.5
- Endpoint: https://urlcheck.ai/mcp (streamable HTTP)
- Source: https://github.com/cybrlab-ai/preclick-mcp
- Website: https://preclick.ai
- GitHub stars: 6
- Registry entry updated: 2026-03-10

## Tools

- Tools it lists (6, about 1,312 tokens of context, `tools/list` without credentials over MCP 2025-06-18, checked 2026-10-04 22:20 UTC):
  - `url_scanner_async_scan` (read-only): Submit a URL for asynchronous security analysis. Returns immediately with a task_id. Poll with url_scanner_async_task_status to check progress, then…
  - `url_scanner_async_scan_with_intent` (read-only): Submit a URL with optional user intent for asynchronous security analysis. Returns immediately with a task_id. Poll with url_scanner_async_task_status to check…
  - `url_scanner_async_task_result` (read-only): Retrieve the result of an asynchronous scan task. If completed, returns the full scan result (risk_score, confidence, agent_access_directive, etc.). If still…
  - `url_scanner_async_task_status` (read-only): Check the status of an asynchronous scan task. Returns the current task status using native MCP task semantics (working, completed, failed, cancelled) without…
  - `url_scanner_scan` (read-only): Analyze a URL for security threats (synchronous, blocks until complete or timeout). Returns risk score, confidence, agent access guidance, and intent_alignment…
  - `url_scanner_scan_with_intent` (read-only): Analyze a URL for security threats with optional user intent context (synchronous, blocks until complete or timeout). Returns risk score, confidence, agent…
- How its tools read to an agent (0 errors, 2 warnings, 1 note, about 1,312 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score):
  - warn TC21 url_scanner_async_scan: described almost the same as url_scanner_async_scan_with_intent (89% of the same words)
  - warn TC21 url_scanner_scan: described almost the same as url_scanner_scan_with_intent (86% of the same words)
  - note TC24 server: 6 of 6 tools have no outputSchema

- JSON: https://www.anchorterminal.com/api/v1/tools/urlcheck-mcp.json
- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming