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.

Brush Pack

REMOTE · BRUSH-PACK.NEROLABS.WORKERS.DEV

Paint and wallpaper amounts, weather checks and lead paint safety for UK decorators' AI

+3 this week 64 Trust /100

Last scanned (16 hours ago)

Scores higher than 46% of remote servers

Reachable. Last reached 21 Nov 2026.

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
  • 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 enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
  • 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 Usability52
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 3216 tokens (~402/item across 8 items; 8 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 Coverage95
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 86% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (12)

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

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • HTTPS in Endpoint SecurityHTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.

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.

  • 20 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 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.

  • 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 61

    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://brush-pack.nerolabs.workers.dev/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=nerolabs.workers.dev CN=YE1,O=Let's Encrypt,C=US 10 Nov 2026 8 Feb 2027 ECDSA 256 ECDSA-SHA384 6de4049323d6abaa327886d7b5c76757b3a
SANs: *.nerolabs.workers.dev, nerolabs.workers.dev
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of brush-pack.nerolabs.workers.dev. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
dev. DS published 60074 8 Verified
workers.dev. 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

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://brush-pack.nerolabs.workers.dev/mcp Verified 200
http (plaintext) http://brush-pack.nerolabs.workers.dev/mcp Inconclusive 405
MCP tools · 8 exposed · ~3,069 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
exterior_weather_check ~600

For a UK postcode (or latitude and longitude) and dates from today up to 8 days ahead, fetches the hourly forecast (MET Norway) and checks each working hour against typical limits for the paint type: minimum temperature, humidity, 3 C above dew point, rain chance, wind, and a rain-free drying time after each coat. Returns each day's verdict (good, good_but_watch_rain, marginal, no), the best painting window, the main problems and an indicative recoat time at that day's temperature. Pass the data sheet's own limits to override. Example: {"postcode":"LS1 4AP","paint_type":"water_based_masonry","start_date":"2026-11-14","end_date":"2026-11-18"}.

NameTypeReqDescription
end_datestring–YYYY-MM-DD, at most 15 days after today. Defaults to start + 6 days.
end_hournumber–Working day end. Defaults to 17.
latitudenumber––
longitudenumber––
max_humidity_percentnumber––
min_temp_cnumber–Minimum application temperature from the data sheet.
paint_typestring–water_based_masonry: Water-based masonry paint, from 8 C, humidity up to 80%, 4 h rain free; solvent_based_masonry: Solvent-based (pliolite type) masonry paint, from 5 C, humidity up to 85%, 2 h rain…
postcodestring–Full UK postcode of the job.
rain_free_hoursnumber–Hours the coat must stay dry after it goes on.
recoat_hours_at_20cnumber–Recoat time at 20 C from the data sheet.
start_datestring–YYYY-MM-DD, today or later. Defaults to today.
start_hournumber–Working day start, 24 hour clock. Defaults to 8.
tradeobject–Optional. The decorator's own business details (Nero Trade Profile v1). Used to prefill quotes and to give a stable nero_trade_ref. Not stored by Brush Pack.

No output schema declared.

No examples provided.

job_estimate ~390

Hours and days on site for a decorating job from rooms (same sizes as paint_quantity, with walls, ceiling and woodwork coats, new_plaster for mist coats) and extra tasks (strip_wallpaper_m2, hang_wallpaper_rolls, hang_patterned_wallpaper_rolls, masonry_smooth_m2_per_coat, masonry_rough_m2_per_coat, door_per_coat, window_per_coat, skirting_m_per_coat, custom_hours), plus prep (light, medium, heavy) and daily set up and clean up. With a day or hourly rate, materials, markup and VAT it gives a priced quote with lines. Rates are indicative for one experienced decorator. Example: {"rooms":[{"name":"Lounge","length_m":4,"width_m":3.5,"height_m":2.4}],"prep_level":"medium","day_rate_gbp":200}.

NameTypeReqDescription
day_rate_gbpnumber–Day rate per decorator, pounds.
decoratorsnumber–People on the job. Defaults to 1.
extra_tasksarray–At most 50.
hourly_rate_gbpnumber–Use instead of a day rate.
hours_per_daynumber–Defaults to 8.
materials_gbpnumber–Cost of materials, pounds.
materials_markup_percentnumber––
prep_levelstring–light: sound surfaces; medium: normal filling and sanding (default); heavy: lots of filling, flaking paint, caulking.
roomsarray–At most 30.
tradeobject–Optional. The decorator's own business details (Nero Trade Profile v1). Used to prefill quotes and to give a stable nero_trade_ref. Not stored by Brush Pack.
vat_registeredboolean–Adds VAT at 20%.

No output schema declared.

No examples provided.

lead_paint_risk ~342

Judges how likely old paint is to contain lead from the build year, surfaces, paint condition and any test result, checks the planned removal methods (dry sanding, blowlamps and dry scraping are refused; wet abrading, chemical strippers and heat guns below about 450 C are allowed with care), and gives the safe test, removal, clean-up and waste steps from HSE and UK guidance, plus the Control of Lead at Work duties. Returns `urgency` only if paint has already been disturbed unsafely. Example: {"build_year":1935,"surfaces":["windows","doors"],"planned_methods":["dry_sanding"],"children_under_6_or_pregnant":true}.

NameTypeReqDescription
already_disturbedboolean–Old paint has already been sanded, scraped or burnt off without lead precautions.
build_yearnumber–Year the home (or the painted item) was built.
children_under_6_or_pregnantboolean–A child under 6 or a pregnant person lives in or visits the home.
erastring–Use if the exact year is unknown.
original_paint_likelyboolean–False if the old layers are known to have been stripped back to bare before. Default true.
paint_conditionstring––
planned_methodsarray––
surfacesarray––
test_resultstring––
tradeobject–Optional. The decorator's own business details (Nero Trade Profile v1). Used to prefill quotes and to give a stable nero_trade_ref. Not stored by Brush Pack.

No output schema declared.

No examples provided.

list_capabilities ~33

Lists Brush Pack's tools, surfaces, paint types and what it deliberately does not do. Free, needs no input.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

paint_quantity ~975

Works out paint for a room (walls, ceiling, woodwork from length, width, height, doors and windows), an exterior (perimeter x height plus gables, less openings) or a custom list of areas. Shows areas, coats, indicative coverage per surface type, litres, litres with waste and the tins to buy (least paint left over, plus a fewer tins option). New plaster adds a mist coat; a light over dark colour change adds a wall coat. Coverage is indicative: pass the tin's figure as coverage_m2_per_litre to make it exact. Example: {"job":"room","length_m":4,"width_m":3.5,"height_m":2.4,"doors":1,"windows":1}.

NameTypeReqDescription
areasarray–Custom: list of { name, area_m2, surface, coats, coverage_m2_per_litre }. At most 100.
ceiling_coatsnumber–Defaults to 2.
ceiling_surfacestring––
colour_changestring–light_over_dark and strong_colour add one wall coat.
coverage_m2_per_litrenumber–Spreading rate from the tin, used for every wall and ceiling line.
door_height_mnumber–Defaults to 1.981.
door_width_mnumber–Defaults to 0.762 (standard 2 ft 6 in door).
doorsnumber–Number of doors. Defaults to 1.
gablesarray–Exterior: gable triangles above the eaves line (width at the base, height to the ridge).
height_mnumber–Wall height floor to ceiling, metres. Defaults to 2.4.
jobstring–Defaults to room, or exterior if perimeter_m is given, or custom if areas is given.
length_mnumber–Room length, metres.
openings_m2number–Exterior: total area of doors and windows to take off.
paint_ceilingboolean–Default true.
paint_wallsboolean–Default true.
paint_woodworkboolean–Default true (skirting, door faces and frames, window frames).
perimeter_mnumber–Exterior: total length of walls to paint, metres.
skirting_height_mnumber–Painted skirting height, defaults to 0.15.
tin_sizes_larray–Tin sizes on offer, litres. Defaults by product: emulsion 10, 5, 2.5, 1; masonry 10, 5, 2.5; trim 2.5, 1, 0.75, 0.5.
tradeobject–Optional. The decorator's own business details (Nero Trade Profile v1). Used to prefill quotes and to give a stable nero_trade_ref. Not stored by Brush Pack.
wall_coatsnumber–Defaults to 2 (plus a mist coat on new plaster).
wall_surfacestring–Surface of the walls. Room default smooth_painted; exterior default masonry_smooth. smooth_painted: Previously painted smooth plaster or plasterboard (12 m2/L); new_plaster: New bare plaster (porous,…
waste_percentnumber–Added to the litres before choosing tins. Defaults to 10.
width_mnumber–Room width, metres.
window_sizesarray–Real window opening sizes.
windowsnumber–Number of windows at the 1.2 x 1.2 m default size. Defaults to 1. Ignored if window_sizes is given.
woodwork_bareboolean–Adds a primer or undercoat coat on the woodwork.
woodwork_coatsnumber–Top coats on woodwork, defaults to 2.

No output schema declared.

No examples provided.

prep_checklist ~225

How to prepare a surface and which paint system goes on it: checks, prep steps, system (primer, undercoat, top coats) and what to avoid, for new_plaster, previously_painted_walls, bare_softwood, mdf, previously_painted_wood, exterior_wood, bare_metal_ferrous, galvanised_or_aluminium, masonry, damp_or_water_stained, smoke_or_nicotine, mould. With `cause` (fire_or_smoke, flood, active_leak, mould) it adds the making good steps and an `urgency` value. Example: {"surfaces":["new_plaster","previously_painted_wood"]}.

NameTypeReqDescription
causestring–Why the work is needed, if it is making good after damage.
surfacestring––
surfacesarray––
tradeobject–Optional. The decorator's own business details (Nero Trade Profile v1). Used to prefill quotes and to give a stable nero_trade_ref. Not stored by Brush Pack.

No output schema declared.

No examples provided.

trade_profile ~158

Checks the decorator's own business details (Nero Trade Profile v1: trading name, Companies House number, trade body and number such as PDA or TrustMark, postcode, contact) and returns them cleaned, with a stable `nero_trade_ref` computed from the trade body membership or company number. The same object, given as `trade` to the other tools, prefills their answers. Brush Pack stores nothing. The same profile and reference can later be used to sign the business into Nero Work, the agent job exchange for trades.

NameTypeReqDescription
tradeobjectyesOptional. The decorator's own business details (Nero Trade Profile v1). Used to prefill quotes and to give a stable nero_trade_ref. Not stored by Brush Pack.

No output schema declared.

No examples provided.

wallpaper_rolls ~346

Rolls of wallpaper for a room or feature wall from wall widths (or room length and width), height, roll width and length (default 10.05 x 0.53 m), pattern repeat and match (free, straight, half drop). Shows drops, cut length, drops per roll and rolls, plus one spare. Example: {"length_m":4,"width_m":3.5,"height_m":2.4,"pattern_repeat_cm":53,"pattern_match":"straight"}.

NameTypeReqDescription
deduct_width_mnumber–Width of near full height openings (patio doors, wide windows) to take off.
height_mnumberyesHeight to paper, metres.
length_mnumber–Room length, if papering all four walls.
pattern_matchstring–Defaults to straight when a repeat is given, otherwise free.
pattern_repeat_cmnumber–Pattern repeat from the roll label, cm. 0 or missing means no repeat.
roll_length_mnumber–Defaults to 10.05.
roll_width_mnumber–Defaults to 0.53.
tradeobject–Optional. The decorator's own business details (Nero Trade Profile v1). Used to prefill quotes and to give a stable nero_trade_ref. Not stored by Brush Pack.
trim_allowance_cmnumber–Total extra per drop for trimming top and bottom. Defaults to 10.
wall_widths_marray–Width of each wall to paper. For one feature wall give one width.
width_mnumber–Room width, if papering all four walls.

No output schema declared.

No examples provided.

Install

How do I install the Brush Pack MCP server?

Brush Pack is a hosted endpoint at https://brush-pack.nerolabs.workers.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 · brush-pack.nerolabs.workers.dev

# add to Claude Code
claude mcp add --transport http nero-engine-brush-pack 'https://brush-pack.nerolabs.workers.dev/mcp'
Common questions

What is the Brush Pack MCP server?

Brush Pack is an MCP server listed in the public MCP registry as io.github.Nero-Engine/brush-pack. Paint and wallpaper amounts, weather checks and lead paint safety for UK decorators' AI. This page covers its hosted endpoint (https://brush-pack.nerolabs.workers.dev/mcp).

Is the Brush Pack MCP server safe to use?

Brush Pack scores 64 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 Brush Pack MCP server expose?

Brush Pack exposes 8 tools: list_capabilities, paint_quantity, wallpaper_rolls, lead_paint_risk, exterior_weather_check, and 3 more. Their descriptions and schemas cost roughly 3,069 tokens of context every time the server is loaded.

Does the Brush Pack MCP server require authentication?

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

Is the Brush Pack MCP server still maintained?

Brush Pack 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 Brush Pack MCP server?

VerifyMCP ran 12 checks on Brush Pack, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Brush Pack: HTTPS. 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.