Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

classifier.dev

REMOTE · CLASSIFIER.DEV · SCANNED SEP 28

Sort up to 1,000 texts into your own labels with a calibrated confidence per answer. No API key.

Available components

+3 this week 68 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability60
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1863 tokens (~372/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management30
  • Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage98
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 94% of tool parameters carry a description.Partial
  • Structured output schemas are declared (80% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the classifier.dev MCP server?

classifier.dev is a hosted endpoint at https://classifier.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · classifier.dev

# add to Claude Code
claude mcp add --transport http dev-classifier-classifier 'https://classifier.dev/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "dev-classifier-classifier": {
      "url": "https://classifier.dev/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "dev-classifier-classifier": {
      "type": "http",
      "url": "https://classifier.dev/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.dev-classifier-classifier]
url = "https://classifier.dev/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-classifier-classifier": {
      "type": "remote",
      "url": "https://classifier.dev/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add dev-classifier-classifier --url 'https://classifier.dev/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  dev-classifier-classifier:
    url: "https://classifier.dev/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "dev-classifier-classifier": {
      "Transport": "http",
      "Url": "https://classifier.dev/mcp"
    }
  }
}
# add to Vellum
assistant mcp add dev-classifier-classifier -t streamable-http -u 'https://classifier.dev/mcp'
// mcp.json
{
  "mcpServers": {
    "dev-classifier-classifier": {
      "type": "http",
      "url": "https://classifier.dev/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 27 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 24 Sept 26 +1
    • “classify_texts” reworded the description of “model” cosmetic

    1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.

  • 23 Sept 26 0
    • “classify_texts” reworded the description of “model” cosmetic

    1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.

  • 22 Sept 26 +1
    • “classify_texts” reworded the description of “model” cosmetic

    1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.

  • 21 Sept 26 −1
    • Tool “classify_texts” rewrote its description, which is the text the model reads security
    • Schema quality: 257 → 296 ▼ functional
    • Tool coverage: 100% → 92% ▼ functional
    • “classify_dimensions” added an optional parameter “model” cosmetic
    • “classify_dimensions” added an optional parameter “processing” cosmetic
    • “classify_multi_label” added an optional parameter “model” cosmetic
    • “classify_multi_label” added an optional parameter “processing” cosmetic
    • “classify_texts” added an optional parameter “model” cosmetic
    • “classify_texts” added an optional parameter “processing” cosmetic
    • “classify_dimensions” reworded the description of “tier” cosmetic
    • “classify_texts” reworded the description of “tier” cosmetic
  • 20 Sept 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool coverage: 100% → 80% ▼ functional
    • Schema quality: 1072 → 1287 ▼ functional
    • Stability: unverified → 0.03 ▲ functional
    • New tool “classify_dimensions” functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 28 Sept 2026 · Probed https://classifier.dev/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=classifier.dev CN=WE1,O=Google Trust Services,C=US 13 Aug 2026 11 Nov 2026 ECDSA 256 ECDSA-SHA256 53f2a38558bc9b850eb3dd68ab54e54b
SANs: classifier.dev, www.classifier.dev, *.www.classifier.dev
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of classifier.dev. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
dev. present 60074 8 Verified
classifier.dev. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://classifier.dev/mcp Verified 200
http (plaintext) http://classifier.dev/mcp Inconclusive 405
MCP tools · 5 exposed · ~1,675 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
classify_dimensions ~329

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.

NameTypeReqDescription
dimensionsobjectyesNamed dimensions. Each is a label array or {labels, instructions}. At most 1,000 item × dimension decisions; definitions at most 16,000 characters combined.
includearray–With url: return article.markdown and/or article.html at no extra scrape cost. Omit for compact output.
instructionsstring–Optional extra criteria, e.g. "judge only the service, ignore the food".
itemsarray–1 to 1,000 texts to classify. Results come back in the same order.
modelstring––
processingstring–Optional. Implies Laya if model is omitted; has no effect with explicit Jev. Omit for automatic fast/bulk selection based on item × dimension decisions.
tierstring–fast (default) or smart, which re-asks answers under 0.7 confidence of a reasoning model (slower, single-label only). Independent of the Laya processing lane.
urlstring–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 ch…

No output schema declared.

No examples provided.

classify_multi_label ~330

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.

NameTypeReqDescription
includearray–With url: return article.markdown and/or article.html at no extra scrape cost. Omit for compact output.
inputsarray–1 to 1,000 texts to classify. Results come back in the same order.
instructionsstring–Optional extra criteria, e.g. "judge only the service, ignore the food".
labelsarrayyes2 to 100 category names. Descriptive names classify better: "urgent bug" beats "p0". Add a label like "none of these" when none-of-the-above is a real outcome.
max_labelsinteger–At most this many labels per text, most likely first.
modelstring––
processingstring–Optional. Implies Laya if model is omitted; has no effect with explicit Jev. Omit to select fast for up to four labels on one text, or bulk for larger work automatically.
urlstring–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 ch…
NameTypeReqDescription
resultsarrayyes–
usageobject––

No examples provided.

classify_texts ~617

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.

NameTypeReqDescription
includearray–With url: return article.markdown and/or article.html at no extra scrape cost. Omit for compact output.
inputsarray–1 to 1,000 texts to classify. Results come back in the same order.
instructionsstring–Optional extra criteria, e.g. "judge only the service, ignore the food".
labelsarrayyes2 to 100 category names. Descriptive names classify better: "urgent bug" beats "p0". Add a label like "none of these" when none-of-the-above is a real outcome.
modelstring–Jev is default. Default/explicit jev inputs over 32,000 characters use paid Fast-only long context: up to 250,000 original cl100k_base context tokens total, 20 documents, 32 decisions and a 1 MB body…
processingstring–Optional. Implies Laya if model is omitted; has no effect with explicit Jev. With Laya, omit to select fast for one decision or bulk for batches automatically. Explicit fast accepts one decision. Sha…
tierstring–fast (default) or smart, which re-asks answers under 0.7 confidence of a reasoning model (slower, single-label only). Independent of the Laya processing lane.
urlstring–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 ch…
NameTypeReqDescription
modelstring––
resultsarrayyesOne per input, in input order.
tierstring––
usageobject––

No examples provided.

count_labels ~201

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.

NameTypeReqDescription
inputsarrayyes1 to 1,000 texts to classify. Results come back in the same order.
instructionsstring–Optional extra criteria, e.g. "judge only the service, ignore the food".
labelsarrayyes2 to 100 category names. Descriptive names classify better: "urgent bug" beats "p0". Add a label like "none of these" when none-of-the-above is a real outcome.
unsure_belownumber–Answers with confidence under this count as unsure.
NameTypeReqDescription
countsobjectyesLabel -> how many texts, every label present.
totalintegeryes–
unsureintegeryesHow many answers fell under unsure_below.
unsure_belownumber––

No examples provided.

review_uncertain ~198

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.

NameTypeReqDescription
belownumber–Return items with confidence under this.
inputsarrayyes1 to 1,000 texts to classify. Results come back in the same order.
instructionsstring–Optional extra criteria, e.g. "judge only the service, ignore the food".
labelsarrayyes2 to 100 category names. Descriptive names classify better: "urgent bug" beats "p0". Add a label like "none of these" when none-of-the-above is a real outcome.
NameTypeReqDescription
belownumber––
totalintegeryes–
uncertainarrayyes–

No examples provided.

Common questions

What is the classifier.dev MCP server?

classifier.dev is an MCP server listed in the public MCP registry as dev.classifier/classifier. Sort up to 1,000 texts into your own labels with a calibrated confidence per answer. No API key. This page covers its hosted endpoint (https://classifier.dev/mcp).

Is the classifier.dev MCP server safe to use?

classifier.dev scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the classifier.dev MCP server expose?

classifier.dev exposes 5 tools: classify_texts, classify_dimensions, classify_multi_label, count_labels, review_uncertain. Their descriptions and schemas cost roughly 1,675 tokens of context every time the server is loaded.

Does the classifier.dev MCP server require authentication?

No. We connected to classifier.dev without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the classifier.dev MCP server still maintained?

classifier.dev is still listed as active in the MCP registry. We last reached this channel on 28 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.