classifier.dev
Server Details
Sort up to 1,000 texts into your own labels with a calibrated confidence per answer. No API key.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- mrmps/classifier-dev
- GitHub Stars
- 423
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 5 tools
Four of the five tools (classify_texts, classify_multi_label, classify_dimensions, count_labels) all classify up to 1,000 texts, so the boundaries are genuinely subtle, but the descriptions give explicit 'use this when' guidance distinguishing single-label, multi-label, multi-dimension, and histogram output shapes. review_uncertain is clearly distinct as a follow-up filter. Only minor confusion is possible between classify_texts and classify_dimensions.
All names are snake_case and follow a verb_noun pattern (classify_texts, count_labels, review_uncertain). The repeated classify_ prefix with slightly inconsistent noun types (texts vs multi_label vs dimensions) is a minor deviation but overall readable and predictable.
Five tools is well-scoped for a text classification service: three classification modes, an aggregation view, and a review step. Each tool earns its place with no redundancy in count.
The surface covers the core classification lifecycle: single-label, multi-label, multi-dimension, aggregate counts, and uncertainty review, which is strong coverage. Minor gaps include no job/batch status handling or model listing, but agents can work around these.
Available Tools
5 toolsclassify_dimensionsClassify several dimensions per textAInspect
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.
Inputs: dimensions (required), url, tier, items, +5 more.
classify_multi_labelTag texts with every label that appliesAInspect
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.
Inputs: labels (required), url, model, inputs, +5 more. Returns: usage, results
classify_textsClassify texts into one label eachAInspect
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 to experimental Laya. so act on the sure ones and look at the rest yourself, or pass tier "smart" to have the unsure ones re-asked of a reasoning model.
Inputs: labels (required), url, tier, model, +5 more. Returns: tier, model, usage, results
count_labelsCount how many texts fall under each labelAInspect
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.
Inputs: inputs (required), labels (required), share_data, instructions, +1 more. Returns: total, counts, unsure, unsure_below
review_uncertainFind the texts the classifier was unsure aboutAInspect
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.
Inputs: inputs (required), labels (required), below, share_data, +1 more. Returns: below, total, uncertain
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Calibrated judgments for text: yes/no probabilities, picks from your options, or scores.
Train a text classifier from your labelled examples in a minute; label texts with probabilities.
Score pages against 11,485 public taxonomy categories by embedding similarity. Free.
Sentiment, toxicity, entity extraction, PII, translation, summary, QA, fraud scoring, safety audit.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to obtain calibrated probabilities, option picks, scale scores, and multi-question judgments for batches of short text, returning numeric results for sorting, filtering, and counting.MIT
- FlicenseNot gradedqualityDmaintenanceClassify raw text into structured triage objects with intent, urgency, category, and sentiment. Zero-config MCP tool for support intake, lead routing, and ticket automation-
- AlicenseNot gradedqualityCmaintenanceEnables structured yes/no, multiple-choice, and ordered-score judgments from supplied text and criteria, returning typed probabilities, selected labels, scores, and confidence. It exposes bounded decision tools without search, chat generation, arbitrary HTTP requests, or action execution.MIT
- AlicenseNot gradedqualityCmaintenanceClassifies text into topic categories with confidence scores, readability metrics, and content type detection, using x402 micropayments for pay-per-call access.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.