Search / app.getstringer/cleanextract
protogridR0· no sign-inConvert public HTML or a public URL into token-dense Markdown through one remote MCP tool.
v0.3.0 · active · descriptor JSON · versions
{
"mcpServers": {
"cleanextract": {
"type": "http",
"url": "https://extract.getstringer.app/mcp"
}
}
}claude mcp add --transport http cleanextract https://extract.getstringer.app/mcp[mcp_servers.cleanextract]
url = "https://extract.getstringer.app/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"cleanextract": {
"type": "remote",
"url": "https://extract.getstringer.app/mcp",
"enabled": true
}
}
}{
"mcpServers": {
"cleanextract": {
"type": "http",
"url": "https://extract.getstringer.app/mcp"
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=cleanextract&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vZXh0cmFjdC5nZXRzdHJpbmdlci5hcHAvbWNwIn0%3D"
}{
"servers": {
"cleanextract": {
"type": "http",
"url": "https://extract.getstringer.app/mcp"
}
}
}{
"mcpServers": {
"cleanextract": {
"httpUrl": "https://extract.getstringer.app/mcp"
}
}
}extensions:
"cleanextract":
enabled: true
name: "cleanextract"
type: streamable_http
uri: "https://extract.getstringer.app/mcp"
timeout: 300
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28protocol.statelessonly applies to 2026-07-28 serversprotocol.transportstreamable HTTPprotocol.list_ttlonly applies to 2026-07-28 serversauth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptionsevery tool has a descriptiontools.description_lengthdescriptions are concisetools.schemasevery tool has an object input schematools.annotationsonly 1 of 2 tools declare readOnlyHint or destructiveHinttools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: clean_extract (readOnlyHint, destructiveHint, idempotentHint); clean_extract_outline (destructiveHint, idempotentHint)tools.token_costabout 579 tokens to load every tooltools.api_dumptools are not a one-to-one API dumpstability.changes4 tool changes in 30 daysstability.rug_pull1 tools kept their name but changed most of their description in 30 days; review before trusting themdeps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI packageclean_extract_outlinechangedtitle, description, annotationsFree 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.
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.
clean_extractchangedtitle, description, annotationsExtract 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.
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_outlineaddedFree 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.
clean_extractchangeddescription, input schemameaning changedConvert a public URL or raw HTML into token-dense markdown. Every response reports extraction_quality, including extraction_content_ratio_band.
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: list_changes · trend: quality JSON.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+dns-namespace +reachable +uptime-96% ~updated-50d-ago -no-repository
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://extract.getstringer.app/mcp streamable-http | none | yes | 96% | 284 ms | 2025-11-25 | 2026-10-19 |
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_outlineread-only | 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. |
Schemas: list_tools.
{
"name": "app.getstringer/cleanextract",
"title": "Stringer CleanExtract",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://extract.getstringer.app/mcp",
"type": "streamable-http"
}
],
"version": "0.3.0",
"description": "Convert public HTML or a public URL into token-dense Markdown through one remote MCP tool."
}