# Stringer CleanExtract
> Convert public HTML or a public URL into token-dense Markdown through one remote MCP tool.
- name: app.getstringer/cleanextract
- version: 0.3.0
- connection class: R0 (autonomous)
- trust: 76/100 flags: no-repository
- quality: 71/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/app.getstringer%2Fcleanextract
- tools: https://api.protogrid.dev/v1/servers/app.getstringer%2Fcleanextract/tools
**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.
## Connection (mcpServers)
```json
{
"mcpServers": {
"cleanextract": {
"type": "http",
"url": "https://extract.getstringer.app/mcp"
}
}
}
```
## Trust
- hygiene: 80
- liveness: 99
- freshness: 85
- provenance: 45
- drivers: +dns-namespace +reachable +uptime-97% ~updated-51d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.
## Quality 71/100 (needs work)
### protocol: 75 (weight 25)
- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers
### authorization: n/a (weight 15)
- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL
### tool hygiene: 79 (weight 30)
- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- warn `tools.annotations`: only 1 of 2 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: clean_extract (readOnlyHint, destructiveHint, idempotentHint); clean_extract_outline (destructiveHint, idempotentHint)
- pass `tools.token_cost`: about 579 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump
### stability: 50 (weight 15)
- pass `stability.changes`: 4 tool changes in 30 days
- fail `stability.rug_pull`: 1 tools kept their name but changed most of their description in 30 days; review before trusting them
### dependencies: n/a (weight 15)
- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package
- tools: 2, about 579 tokens to load them all
- tool set hash: 5450a6b59b1bd7ad150f0049278601f0
- tools last changed: 2026-10-06T17:25:08.991Z
- badge: [](https://protogrid.dev/servers/app.getstringer/cleanextract)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.
### Tool changes
- 2026-10-06 `clean_extract_outline` changed (title, description, annotations)
- before: Free outline with section ids, headings, byte sizes, and a fingerprint, without page body text or payment. A later clean_extract call can select sections and is charged only when it returns usable content. Uncharged failures name upstream_timeout, upstream_http_error, bot_challenge, js_shell, empty_extraction, or sections_not_found. Recoverable structured data names fallback_used.
- after: Free outline with section ids, headings, byte sizes, and a fingerprint, without page body text or payment. It never uses the free extraction allowance. Use it first to see what a long page contains and which sections are worth reading. A later clean_extract call can select sections and is charged only when it returns usable content. Uncharged failures name upstream_timeout, upstream_http_error, bot_challenge, js_shell, empty_extraction, or sections_not_found. Recoverable structured data names fallback_used.
- 2026-10-06 `clean_extract` changed (title, description, annotations)
- before: Extract a full page or selected sections from a public URL or raw HTML. A call is charged only when it returns usable content; the first 3 usable extraction calls are free, total, then USD 0.05. Use the free clean_extract_outline first. Uncharged failures name upstream_timeout, upstream_http_error, bot_challenge, js_shell, empty_extraction, or sections_not_found. Recoverable structured data names fallback_used. Every success reports extraction_quality and extraction_content_ratio_band.
- after: Extract a full page or selected sections from a public URL or raw HTML as clean Markdown, with navigation, scripts and page chrome removed. Use it instead of a raw fetch when a task needs the text of documentation, an article, an RFC or another reference page: in a five-site benchmark the Markdown was 62% fewer estimated tokens than the HTML. Call the free clean_extract_outline first on a long page, then pass only the section ids you need. A call is charged only when it returns usable content; the first 3 usable extraction calls are free, total, then USD 0.05. Uncharged failures name upstream_timeout, upstream_http_error, bot_challenge, js_shell, empty_extraction, or sections_not_found. Recoverable structured data names fallback_used. Every success reports extraction_quality and extraction_content_ratio_band.
- 2026-09-25 `clean_extract_outline` added
- Free outline with section ids, headings, byte sizes, and a fingerprint, without page body text or payment. A later clean_extract call can select sections and is charged only when it returns usable content. Uncharged failures name upstream_timeout, upstream_http_error, bot_challenge, js_shell, empty_extraction, or sections_not_found. Recoverable structured data names fallback_used.
- 2026-09-25 `clean_extract` changed (description, inputSchema) **meaning changed**
- before: Convert a public URL or raw HTML into token-dense markdown. Every response reports extraction_quality, including extraction_content_ratio_band.
- after: Extract a full page or selected sections from a public URL or raw HTML. A call is charged only when it returns usable content; the first 3 usable extraction calls are free, total, then USD 0.05. Use the free clean_extract_outline first. Uncharged failures name upstream_timeout, upstream_http_error, bot_challenge, js_shell, empty_extraction, or sections_not_found. Recoverable structured data names fallback_used. Every success reports extraction_quality and extraction_content_ratio_band.
Full history: https://api.protogrid.dev/v1/servers/app.getstringer%2Fcleanextract/changes
## Remotes
- https://extract.getstringer.app/mcp (streamable-http, auth none, reachable true, uptime30d 0.9652174)
## Packages
_none_
## Tools (2)
- `clean_extract`: Extract a full page or selected sections from a public URL or raw HTML as clean Markdown, with navigation, scripts and page chrome removed. Use it instead of a raw fetch when a task needs the text of documentation, an article, an RFC or another reference page: in a five-site benchmark the Markdown was 62% fewer estimated tokens than the HTML. Call the free clean_extract_outline first on a long page, then pass only the section ids you need. A call is charged only when it returns usable content; the first 3 usable extraction calls are free, total, then USD 0.05. Uncharged failures name upstream_timeout, upstream_http_error, bot_challenge, js_shell, empty_extraction, or sections_not_found. Recoverable structured data names fallback_used. Every success reports extraction_quality and extraction_content_ratio_band.
- `clean_extract_outline`: Free outline with section ids, headings, byte sizes, and a fingerprint, without page body text or payment. It never uses the free extraction allowance. Use it first to see what a long page contains and which sections are worth reading. A later clean_extract call can select sections and is charged only when it returns usable content. Uncharged failures name upstream_timeout, upstream_http_error, bot_challenge, js_shell, empty_extraction, or sections_not_found. Recoverable structured data names fallback_used.