classifier.dev

Name: classifier.dev
Author: Michael Ryaboy

AgentA2AMCP

Zero-shot text classification over plain HTTP. Free without a key; paid plans raise rate limits 10-100x. Sort up to 1,000 texts into your own labels in one call with a calibrated confidence per answer. This service's live agent interface is MCP (Streamable HTTP) at the URL below; A2A message/send i…

Until 2026-09-25 this record combined several servers published from one repository. The others now have records of their own: classifier.dev docs MCP server. Checks from before that date include them.

by Michael Ryaboyrepository ↗homepage ↗v1.0.0

Is this yours?

This record is unclaimed

Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.

Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"classifier-dev","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.

Claim this record

Observed by Wellknown

Evidence

Everything here was measured by our prober or read from a registry. Nothing is self-reported.

30-day availability88/88 checks ok

when	check	result	http	latency	detail
2 h ago	mcp initialize	ok	200	224 ms	server classifier.dev 1.0.0 · protocol 2025-06-18 · 5 tools
9 h ago	mcp initialize	ok	200	211 ms	server classifier.dev 1.0.0 · protocol 2025-06-18 · 5 tools
16 h ago	mcp initialize	ok	200	198 ms	server classifier.dev 1.0.0 · protocol 2025-06-18 · 5 tools
22 h ago	mcp initialize	ok	200	166 ms	server classifier.dev 1.0.0 · protocol 2025-06-18 · 5 tools
29 h ago	mcp initialize	ok	200	216 ms	server classifier.dev 1.0.0 · protocol 2025-06-18 · 5 tools
35 h ago	mcp initialize	ok	200	181 ms	server classifier.dev 1.0.0 · protocol 2025-06-18 · 5 tools
2 d ago	mcp initialize	ok	200	191 ms	server classifier.dev 1.0.0 · protocol 2025-06-18 · 5 tools
2 d ago	mcp initialize	ok	200	166 ms	server classifier.dev 1.0.0 · protocol 2025-06-18 · 5 tools
2 d ago	mcp initialize	ok	200	180 ms	server classifier.dev 1.0.0 · protocol 2025-06-18 · 5 tools
3 d ago	mcp initialize	ok	200	169 ms	server classifier.dev 1.0.0 · protocol 2025-06-18 · 5 tools

Tools observed via MCP handshake

classify_texts — 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 bucke
classify_dimensions — 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. At
classify_multi_label — 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 a
count_labels — 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 shape
review_uncertain — 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

Declared by sources

What the publisher says

Attributed to the source that supplied each field. Treated as claims, not facts.

classificationtextzero-shottriagelabelsmcpa2adiscovery

Declared skills

Classify texts into one label each — 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 bucket and do not want to read them all: search results before opening them, tickets, log lines, changed files, feedback. Do not use it for fewer than about five items you can already see — just decide. For default Jev, confidence is calibrated (answers >= 0.9 are right ~82-92% of the time; < 0.5 about 30-60%); these measurements do not apply…
Classify several dimensions per text — 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. At most 1,000 item × dimension decisions; every field counts toward the quota. Use per-dimension instructions to define ambiguous categories.
Tag texts with every label that applies — 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 article, components touched by a ticket — where one answer is not enough. Set max_labels to cap how many come back per text. Labels scoring >= 0.7 are kept.
Count how many texts fall under each label — 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 shape of a corpus — what share of feedback is bugs vs praise, how many search results are relevant — without pulling a thousand individual answers into context. Use classify_texts when you need the answer per item.
Find the texts the classifier was unsure about — 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 a bulk classification to decide which items deserve your own attention: the confident answers can be trusted, these are the ones to read. Returns the index of each item so you can map back to your list.

kind A2A Agent Card

name A2A Agent Card

repoUrl ARD catalog (/.well-known/ard.json)

summary A2A Agent Card

version A2A Agent Card

description A2A Agent Card

homepageUrl A2A Agent Card

publisherUrl A2A Agent Card

publisherName A2A Agent Card

Provenance

Where this record came from

Every source is kept verbatim. Field changes are logged as events.

A2A Agent Cardhttps://classifier.dev/.well-known/agent-card.json

first seen 19 d ago · fetched 5 d agoopen ↗

ARD catalog (/.well-known/ard.json)urn:air:classifier.dev:mcp:classifier

first seen 19 d ago · fetched 5 d agoopen ↗

ARD catalog (/.well-known/ard.json)urn:air:classifier.dev:agent:classifier

first seen 19 d ago · fetched 5 d agoopen ↗

Official MCP Registrydev.classifier/classifier

first seen 19 d ago · fetched 11 h agoopen ↗

Field history (12 recent events)

5 d ago · declared · summary → "Zero-shot text classification over plain HTTP. Free without a key; paid plans raise rate limits 10-100x. Sort up to 1,0
5 d ago · declared · description → "Zero-shot text classification over plain HTTP. Free without a key; paid plans raise rate limits 10-100x. Sort up to 1,0
19 d ago · declared · summary → "Zero-shot text classification over plain HTTP. Free without a key; Pro for 10x limits. Sort up to 1,000 texts into your
19 d ago · declared · kind → "agent"
19 d ago · declared · description → "Zero-shot text classification over plain HTTP. Free without a key; Pro for 10x limits. Sort up to 1,000 texts into your
19 d ago · declared · publisherName → "Michael Ryaboy"
19 d ago · declared · publisherUrl → "https://classifier.dev"
19 d ago · declared · homepageUrl → "https://classifier.dev/developers"
19 d ago · declared · protocols → ["a2a","mcp"]
19 d ago · declared · description → "Sort up to 1,000 texts into your own labels with a calibrated confidence per answer. No API key."
19 d ago · declared · homepageUrl → "https://classifier.dev"
19 d ago · declared · repoUrl → "https://github.com/mrmps/classifier-dev"

This record is unclaimed

Evidence

What the publisher says

Capabilities

Where this record came from