Feature Request
When conducting large-scale research (400+ sources), there is no way to validate that collected URLs are still live and accessible. A bulk URL health check tool would significantly improve research quality.
Use Case
After collecting 400 sources across 8 research domains, I need to:
- Verify all URLs are still accessible (not 404, paywall-only, or redirected)
- Detect duplicate URLs that appear in multiple source lists
- Identify sources that have been updated since collection
Proposed Tool: source_validation
{
"operation": "validate_urls",
"urls": ["url1", "url2", ...], // up to 100 URLs per call
"checks": ["status_code", "redirect", "paywall_detection", "last_modified"]
}Returns:
{
"results": [
{"url": "...", "status": 200, "redirected": false, "paywall": false, "last_modified": "..."},
{"url": "...", "status": 404, "error": "Not Found"},
...
],
"summary": {"live": 95, "dead": 3, "paywalled": 2}
}Alternative: Extend content_operations score
The existing score operation could be extended with a validate: true flag that checks URL liveness in addition to quality scoring.
Impact
For research reports being sold or published, source link integrity is critical. A single broken citation undermines credibility. Currently, the only option is manually checking each URL or writing a custom script.
Feature Request
When conducting large-scale research (400+ sources), there is no way to validate that collected URLs are still live and accessible. A bulk URL health check tool would significantly improve research quality.
Use Case
After collecting 400 sources across 8 research domains, I need to:
Proposed Tool:
source_validation{ "operation": "validate_urls", "urls": ["url1", "url2", ...], // up to 100 URLs per call "checks": ["status_code", "redirect", "paywall_detection", "last_modified"] }Returns:
{ "results": [ {"url": "...", "status": 200, "redirected": false, "paywall": false, "last_modified": "..."}, {"url": "...", "status": 404, "error": "Not Found"}, ... ], "summary": {"live": 95, "dead": 3, "paywalled": 2} }Alternative: Extend
content_operations scoreThe existing
scoreoperation could be extended with avalidate: trueflag that checks URL liveness in addition to quality scoring.Impact
For research reports being sold or published, source link integrity is critical. A single broken citation undermines credibility. Currently, the only option is manually checking each URL or writing a custom script.