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.

Clearbar model verdicts

REMOTE · CLEARBAR.GRAIN64.COM

Cheapest LLM that passes each task: cost per successful task and pass rate on public datasets.

+2 this week 74 Trust /100

Last scanned (22 hours ago)

Scores higher than 60% of remote servers

Reachable. Last reached 21 Nov 2026.

Category AI and Machine Learning

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 Security74
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability70
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 662 tokens (~220/item across 3 items; 3 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 Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% 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 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 4 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
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

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.

  • 21 Nov 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.

  • 19 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: 449 → 662 ▼ functional
    • Server version: 1.2.0 → 1.3.0 functional
    • New tool “cheapest_model” functional
  • 18 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Nov 26 −1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “get_verdict” rewrote its description, which is the text the model reads security
    • Tool “list_verdicts” rewrote its description, which is the text the model reads security
    • Schema quality: pass → fail ▼ functional
    • Server version: 1.1.0 → 1.2.0 functional
    • “get_verdict” added an optional parameter “task” cosmetic
    • “get_verdict” reworded the description of “slug” cosmetic
    • “get_verdict” made “slug” optional cosmetic
  • 15 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Nov 26 0
    • Stability: unverified → 0.03 ▲ functional
  • 13 Nov 26 72

    First indexed and scored.

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 21 Nov 2026 · Probed https://clearbar.grain64.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=clearbar.grain64.com CN=WE1,O=Google Trust Services,C=US 4 Nov 2026 2 Feb 2027 ECDSA 256 ECDSA-SHA256 855e0099a9bae2ac132b79f07bcec1d4
SANs: clearbar.grain64.com
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 clearbar.grain64.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
grain64.com. No DS 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
Header Value
x-content-type-options nosniff

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://clearbar.grain64.com/mcp Verified 200
http (plaintext) http://clearbar.grain64.com/mcp HTTPS enforced 301 https://clearbar.grain64.com/mcp
MCP tools · 3 exposed · ~466 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
cheapest_model ~159

One call, the headline answer: which is the cheapest LLM that still passes? With no arguments you get every task family (classification, extraction, tool-call) with its cheapest passing model, cost per successful task in US dollars (retries and failures counted), how much cheaper it is than the baseline, and the verdict page that proves it. Pass {"task":"spam detection"} (plain words, or a family such as classification) for just that answer. Next call: get_verdict with the slug for the full candidate table, failures and the re-run script.

NameTypeReqDescription
taskstring–Optional. The task in plain words (spam detection, sentiment, json extraction, tool calling) or a family: classification, extraction, tool-call.
NameTypeReqDescription
answersarrayyes–
app_notestringyes–
app_urlstringyesWhere to run the same verdict on your own examples.
countintegeryesNumber of answers returned.
headlinestringyesThe overview in one or two sentences.
next_callstringyesThe call to make next for the full table of one verdict.
prices_as_ofstring|nullyesDate (YYYY-MM-DD) of the newest price snapshot behind the figures.

No examples provided.

get_verdict ~192

Answers: which is the cheapest LLM that still passes for <task>? Give the task in plain words (for example "spam detection", "sentiment", "json extraction", "tool calling", "intent classification") or a verdict slug, and get the cheapest model that clears the bar, its pass rate and cost per successful task in US dollars, the baseline it is compared with, every candidate's status, plus links to the verdict page, the run file (JSON) and the script that re-runs it. Example: {"task":"spam detection"} returns the sms-spam verdict. Not sure what exists? Call list_verdicts first.

NameTypeReqDescription
slugstring–Or the exact verdict slug from list_verdicts, for example sms-spam.
taskstring–The task in plain words, for example spam detection, sentiment, json extraction. The closest published verdict answers.
NameTypeReqDescription
answerstringyesOne-sentence verdict in plain words, with the price date.
app_notestring––
app_urlstringyes–
baseline_cost_per_successful_task_usdnumber|null––
baseline_modelstring|nullyes–
baseline_pass_ratenumber|null––
candidatesarrayyes–
cheapest_passing_modelstring|nullyesThe cheapest model that clears the bar; null when none does.
cost_per_successful_task_usdnumber|nullyesUS dollars per successful task, retries and failures counted.
datasetobject–Public dataset behind the run: name, rows, source, licence.
matched_bystring–How the verdict was chosen: the exact slug, or the closest published verdict to the task you described.
pass_barnumberyesPass-rate threshold the cheapest model has to clear (0 to 1).
pass_ratenumber|null––
price_snapshot_atstring|null––
ran_atstring|null––
rerun_script_urlstring|null–Script that re-runs the verdict; null when none is published.
run_file_urlstringyesThe run file (JSON) to check the figures.
saving_pctnumber|null––
slugstringyesVerdict slug, the key for get_verdict.
taskstringyesTask type, for example classification.
titlestringyes–
verdict_kindstringyesswitch (a cheaper model passes) or keep (the baseline is already cheapest).
verdict_urlstringyesThe verdict page, with the evidence.

No examples provided.

list_verdicts ~115

Which LLM is the cheapest that still passes? Lists every published Clearbar verdict at once: the task, the pass bar, the cheapest passing model, its cost per successful task (retries and failures counted) and the page to check it. Optional filter by task type. Next call: get_verdict with {"task":"spam detection"} (or a slug from this list) for the full table.

NameTypeReqDescription
taskstring–Only verdicts of this task type, for example classification, extraction or tool-call.
NameTypeReqDescription
app_notestringyes–
app_urlstringyesWhere to run the same verdict on your own examples.
countintegeryesNumber of verdicts returned.
next_callstring–The call to make next for the full table of one verdict.
prices_as_ofstring|nullyesDate (YYYY-MM-DD) of the newest price snapshot behind the figures.
verdictsarrayyes–

No examples provided.

Install

How do I install the Clearbar model verdicts MCP server?

Clearbar model verdicts is a hosted endpoint at https://clearbar.grain64.com/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 · clearbar.grain64.com

# add to Claude Code
claude mcp add --transport http com-grain64-clearbar 'https://clearbar.grain64.com/mcp'
Common questions

What is the Clearbar model verdicts MCP server?

Clearbar model verdicts is an MCP server listed in the public MCP registry as com.grain64/clearbar. Cheapest LLM that passes each task: cost per successful task and pass rate on public datasets. This page covers its hosted endpoint (https://clearbar.grain64.com/mcp).

Is the Clearbar model verdicts MCP server safe to use?

Clearbar model verdicts scores 74 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 Clearbar model verdicts MCP server expose?

Clearbar model verdicts exposes 3 tools: cheapest_model, list_verdicts, get_verdict. Their descriptions and schemas cost roughly 466 tokens of context every time the server is loaded.

Does the Clearbar model verdicts MCP server require authentication?

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

Is the Clearbar model verdicts MCP server still maintained?

Clearbar model verdicts is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Clearbar model verdicts MCP server?

VerifyMCP ran 13 checks on Clearbar model verdicts, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.