Fetch URL
fetchRetrieve any public or authenticated URL as readable Markdown with source, timestamp, and content hash. Handles GitHub, Wikipedia, YouTube, PDFs, arXiv, and tweets, with tiered fallbacks and pagination.
Instructions
Fetch a public or authenticated URL as readable Markdown, with source, retrieval time, content hash and completeness. Specialized handlers support GitHub, Wikipedia, YouTube transcripts, PDFs, arXiv and tweets. Otherwise checks fresh shared content, then native Markdown/direct HTML, hosted rendering, and labeled archive fallbacks. Authenticated requests use direct sources only. Paginate long pages with startIndex and maxLength. noCache forces retrieval and disables archives unless explicitly allowed.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "<url>"
},
"name": "fetch"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The URL to fetch | |
| maxTier | No | Stop at this tier (1-5, default 5). Lower = faster but fewer fallbacks. | |
| noCache | No | Skip session and shared caches and fetch live content | |
| maxLength | No | Maximum characters to return (default 50000) | |
| timeoutMs | No | Overall retrieval deadline in milliseconds, including downloads (default 25000) | |
| startIndex | No | Character offset to start from, for paginating long content (default 0) | |
| allowArchive | No | Allow labeled historical snapshots after live retrieval fails; disabled by noCache unless explicitly enabled | |
| maxAgeSeconds | No | Oldest acceptable cached retrieval in seconds; 0 forces retrieval (default 3600) |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| bytes | No | Image size in bytes, when an image was returned | |
| title | No | ||
| source | Yes | ||
| timing | Yes | ||
| quality | Yes | ||
| mimeType | No | Set when the URL is an image returned as an image block | |
| truncated | Yes | ||
| archivedAt | No | ||
| sourceKind | No | ||
| verifiedAt | No | ||
| contentHash | No | ||
| retrievedAt | No | ||
| canonicalUrl | No | ||
| completeness | No | ||
| contentLength | Yes | Full length of the fetched content in characters | |
| nextStartIndex | No | Pass as startIndex to fetch the next chunk | |
| returnedLength | Yes | ||
| cacheAgeSeconds | No | Age of the content when served from the shared cache |