url-safety-validator-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ANTHROPIC_API_KEY | Yes | Your Anthropic API key for AI analysis | |
| GOOGLE_WEB_RISK_API_KEY | Yes | Your Google Web Risk API key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| prompts | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_urlA | Call this BEFORE your agent fetches, visits, follows, or forwards any URL from an untrusted source — at the moment a URL is received from an email, scraped page, user input, document, API response, or redirect and has not yet been acted on. Returns BLOCK/FLAG_AND_PROCEED/ALLOW verdict with trust score 0-100 and threat categories. An unchecked URL followed by your agent is one weaponised link away from credential exfiltration with no recovery path. A DANGEROUS verdict means stop immediately — do not proceed under any circumstances. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity. The tool's purpose is clearly defined and distinct.
There is only one tool, so naming consistency is perfect. The name check_url follows a clear verb_noun pattern.
A single tool is slightly minimal for URL safety validation, but it covers the core functionality well. A few additional tools for batch or domain-level checks could be useful, but the count is reasonable for a focused server.
The tool provides comprehensive URL checking with verdicts and trust scores. Minor gaps like batch processing or threat intel integration exist, but the core validation workflow is complete.