Every change Wellknown observed on this agent, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Changed the definition of "classify_dimensions", "classify_multi_label", "classify_texts" and 2 more
⟨209 unchanged words⟩ ,"bulk"],"type":"string"},"share_data":{"default":true,"description":"Synchronous classification request text, labels, instructions and model results are retained for model training and operator review in private Cloudflare storage by default. Shared requests receive double per-minute and daily classification quotas. Set share_data: false or X-Classifier-Share-Data: false to opt out and use standard limits. Share only data you have permission to contribute; do not include confidential or personal information. Redaction is best effort. Billing, spending caps and input-size limits still apply.","type":"boolean"},"tier":{"description":"fast (default) or ⟨70 unchanged words⟩
{"destructiveHint":false,"idempotentHint":false,"openWorldHint":true,"readOnlyHint":truefalse,"title":"Classify several dimensions per text"}
⟨183 unchanged words⟩ ,"bulk"],"type":"string"},"share_data":{"default":true,"description":"Synchronous classification request text, labels, instructions and model results are retained for model training and operator review in private Cloudflare storage by default. Shared requests receive double per-minute and daily classification quotas. Set share_data: false or X-Classifier-Share-Data: false to opt out and use standard limits. Share only data you have permission to contribute; do not include confidential or personal information. Redaction is best effort. Billing, spending caps and input-size limits still apply.","type":"boolean"},"url":{"description":"Scrape one public URL ⟨38 unchanged words⟩
{"destructiveHint":false,"idempotentHint":false,"openWorldHint":true,"readOnlyHint":truefalse,"title":"Tag texts with every label that applies"}
⟨274 unchanged words⟩ ,"bulk"],"type":"string"},"share_data":{"default":true,"description":"Synchronous classification request text, labels, instructions and model results are retained for model training and operator review in private Cloudflare storage by default. Shared requests receive double per-minute and daily classification quotas. Set share_data: false or X-Classifier-Share-Data: false to opt out and use standard limits. Share only data you have permission to contribute; do not include confidential or personal information. Redaction is best effort. Billing, spending caps and input-size limits still apply.","type":"boolean"},"tier":{"description":"fast (default) or ⟨70 unchanged words⟩
{"destructiveHint":false,"idempotentHint":false,"openWorldHint":true,"readOnlyHint":truefalse,"title":"Classify texts into one label each"}
⟨82 unchanged words⟩ "minItems":2,"type":"array"},"share_data":{"default":true,"description":"Synchronous classification request text, labels, instructions and model results are retained for model training and operator review in private Cloudflare storage by default. Shared requests receive double per-minute and daily classification quotas. Set share_data: false or X-Classifier-Share-Data: false to opt out and use standard limits. Share only data you have permission to contribute; do not include confidential or personal information. Redaction is best effort. Billing, spending caps and input-size limits still apply.","type":"boolean"},"unsure_below":{"default":0.7,"description":"Answers ⟨18 unchanged words⟩
{"destructiveHint":false,"idempotentHint":truefalse,"openWorldHint":falsetrue,"readOnlyHint":truefalse,"title":"Count how many texts fall under each label"}
⟨97 unchanged words⟩ 100,"minItems":2,"type":"array"},"share_data":{"default":true,"description":"Synchronous classification request text, labels, instructions and model results are retained for model training and operator review in private Cloudflare storage by default. Shared requests receive double per-minute and daily classification quotas. Set share_data: false or X-Classifier-Share-Data: false to opt out and use standard limits. Share only data you have permission to contribute; do not include confidential or personal information. Redaction is best effort. Billing, spending caps and input-size limits still apply.","type":"boolean"}},"required":["inputs","labels"],"type":"object"}
{"destructiveHint":false,"idempotentHint":truefalse,"openWorldHint":falsetrue,"readOnlyHint":truefalse,"title":"Find the texts the classifier was unsure about"}
Servers that share this record's repository now have records of their own: "classifier-dev-docs-mcp-server". Checks before this date include them.
Changed the definition of "classify_dimensions", "classify_multi_label" and "classify_texts"
{"additionalProperties":false,"oneOf":[{"not":{"required":["url"]},"required":["items"]},{"not":{"required":["items"]},"required":["url"]}],"properties":{"dimensions":{"additionalProperties":{"oneOf ⟨84 unchanged words⟩ :"\\S"},"type":"object"},"include":{"description":"With url: return article.markdown and/or article.html at no extra scrape cost. Omit for compact output.","items":{"enum":["markdown","html"],"type":"string"},"type":"array"},"instructions":{"description":"Optional extra criteria, ⟨105 unchanged words⟩ fast","smart"],"type":"string"}},"requiredurl":[{"itemsdescription":"Scrape one public URL instead of inputs/items. Requires funded workspace access. Context.dev costs $0.0022 per billed attempt plus classification; long articles need Fast. Errors disclose retained charges. No automatic scrape retries."
Changed the definition of "classify_texts"
⟨85 unchanged words⟩ :"array"},"model":{"description":"OptionalJevmodelsis default. Default/explicit jev inputs over 32,000 characters use paid Fast-only long context:'laya'up(ModernBERT-largeto 250,000512-tokenoriginal cl100k_base context)ortokens'kev'total,(Qwen2.5-0.5B
Changed the definition of "classify_dimensions", "classify_multi_label" and "classify_texts"
⟨138 unchanged words⟩ "enum":["jev","laya","kev","chunklaya"],"type":"string"},"processing":{ ⟨66 unchanged words⟩
⟨105 unchanged words⟩ "enum":["jev","laya","kev","chunklaya"],"type":"string"},"processing":{ ⟨42 unchanged words⟩
Certificate recorded, valid to 2026-11-11
Authorization not required
Changed the definition of "classify_dimensions", "classify_multi_label" and "classify_texts"
⟨137 unchanged words⟩ model":{"enum":["jev","laya","kev"],"type":"string"},"processing":{ ⟨66 unchanged words⟩
⟨104 unchanged words⟩ model":{"enum":["jev","laya","kev"],"type":"string"},"processing":{ ⟨42 unchanged words⟩
Certificate recorded, valid to 2026-11-11
Authorization not required
Unknown → Live
First tool surface recorded: 4 tools (server version 1.0.0)
First tool surface recorded: 5 tools (server version 1.0.0)
https://classifier.dev/mcp/docs (mcp_streamable_http) — from mcp_registry
https://classifier.dev/mcp (mcp_streamable_http) — from mcp_registry, with the record
Showing the latest 15 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
{"destructiveHint":false,"idempotentHint":truefalse,"openWorldHint":falsetrue,"readOnlyHint":true,"title":"Classify several dimensions per text"}
{"additionalProperties":false,"oneOf":[{"not":{"required":["url"]},"required":["inputs"]},{"not":{"required":["inputs"]},"required":["url"]}],"properties":{"include":{"description":"With url: return article.markdown and/or article.html at no extra scrape cost. Omit for compact output.","items":{"enum":["markdown","html"],"type":"string"},"type":"array"},"inputs":{"description":"1 to 1,000 ⟨137 unchanged words⟩ fast","bulk"],"type":"string"}},"requiredurl":[{"inputsdescription":"Scrape one public URL instead of inputs/items. Requires funded workspace access. Context.dev costs $0.0022 per billed attempt plus classification; long articles need Fast. Errors disclose retained charges. No automatic scrape retries.","maxLength":8192,"pattern":"^https?://","type":"string"}},"required":["labels"],"type":"object"}
{"destructiveHint":false,"idempotentHint":truefalse,"openWorldHint":falsetrue,"readOnlyHint":true,"title":"Tag texts ⟨5 unchanged words⟩
{"additionalProperties":false,"oneOf":[{"not":{"required":["url"]},"required":["inputs"]},{"not":{"required":["inputs"]},"required":["url"]}],"properties":{"include":{"description":"With url: return article.markdown and/or article.html at no extra scrape cost. Omit for compact output.","items":{"enum":["markdown","html"],"type":"string"},"type":"array"},"inputs":{"description":"1 to 1,000 ⟨259 unchanged words⟩ fast","smart"],"type":"string"}},"requiredurl":[{"inputsdescription":"Scrape one public URL instead of inputs/items. Requires funded workspace access. Context.dev costs $0.0022 per billed attempt plus classification; long articles need Fast. Errors disclose retained charges. No automatic scrape retries.","maxLength":8192,"pattern":"^https?://","type":"string"}},"required":["labels"],"type":"object"}
{"destructiveHint":false,"idempotentHint":truefalse,"openWorldHint":falsetrue,"readOnlyHint":true,"title":"Classify texts ⟨4 unchanged words⟩
⟨85 unchanged words⟩ array"},"model":{"description":"OptionalBeam-hostedmodels: 'laya' (ModernBERT-large, 512-token context) or 'kev' (Qwen2.5-0.5B with a pointer head, 8K context)., or 'chunklaya', our long-document model (up to 4,000,000 characters, 20 inputs per request), which is also chosen automatically for any input over 32,000 characters. Jev remains the default.","enum":["jev","laya","kev","chunklaya"],"type":"string"},"processing": ⟨80 unchanged words⟩
⟨85 unchanged words⟩ array"},"model":{"description":"OptionalLayaBeam-hostedtrialmodels: 'laya' (ModernBERT-large, 512-token context) or 'kev' (Qwen2.5-0.5B withautomaticaEnglish/multilingualpointercheckpointhead,routing;8K context). Jev remains the default.","enum":["jev","laya","kev"],"type":"string"},"processing": ⟨80 unchanged words⟩