# classifier.dev

> classifier.dev, an MCP server by classifier.dev, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Sort up to 1,000 texts into your own labels with a calibrated confidence per answer. No API key.

- Canonical: https://www.anchorterminal.com/tools/classifier
- Markdown: https://www.anchorterminal.com/tools/classifier.md (~900 tokens)
- Slim: https://www.anchorterminal.com/tools/classifier.min.md (~830 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/tools/classifier.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-04

# classifier.dev

> Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/

- Kind: MCP server, by classifier.dev (https://classifier.dev)
- Listed because: It's published in the registry under classifier.dev, a namespace the registry only gives to whoever proves they control that domain. It's in real use: 422 GitHub stars.
- What the official MCP registry says: Sort up to 1,000 texts into your own labels with a calibrated confidence per answer. No API key.

## Facts

- MCP registry: `dev.classifier/classifier` 1.0.0
- Endpoint: https://classifier.dev/mcp (streamable HTTP)
- Source: https://github.com/mrmps/classifier-dev
- Website: https://classifier.dev
- GitHub stars: 422
- Registry entry updated: 2026-09-19

## Tools

- Tools it lists (5, about 3,514 tokens of context, `tools/list` without credentials over MCP 2025-11-25, checked 2026-10-03 22:17 UTC):
  - `classify_texts` (read-only): Sort up to 1,000 texts into exactly one of your own labels each, with confidence per answer. Use this when you have many items to triage, route, filter or…
  - `classify_dimensions` (read-only): Classify each text by several named dimensions, such as team, urgency and kind, in one request. Returns a label, confidence, scores and model for each field.…
  - `classify_multi_label` (read-only): Like classify_texts, but each text gets every label that applies (possibly none), with an independent 0-1 score per label. Use this for tagging — topics of an…
  - `count_labels` (read-only): Classify up to 1,000 texts and return only a histogram: how many landed on each label, and how many the model was unsure about. Use this when you want the…
  - `review_uncertain` (read-only): Classify up to 1,000 texts and return only the ones whose confidence fell under a threshold (default 0.7), each with its two most likely labels. Use this after…
- How its tools read to an agent (0 errors, 5 warnings, 1 note, about 3,514 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score):
  - warn TC11 classify_dimensions: 1 parameter without a description: model
  - warn TC11 classify_multi_label: 1 parameter without a description: model
  - warn TC15 classify_dimensions: inputSchema has oneOf at the top level
  - warn TC15 classify_multi_label: inputSchema has oneOf at the top level
  - warn TC15 classify_texts: inputSchema has oneOf at the top level
  - note TC24 server: 1 of 5 tools have no outputSchema

- JSON: https://www.anchorterminal.com/api/v1/tools/classifier.json
- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming