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.

HardCopy Labs

REMOTE · MCP.HARDCOPYLABS.COM

Order real 3D prints from chat: send an STL or OpenSCAD model, see one price, get it by UPS.

0 this week 85 Trust /100

Last scanned (19 hours ago)

Scores higher than 86% of remote servers

Reachable. Last reached 21 Nov 2026.

Category E-commerce

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 Usability74
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2299 tokens (~383/item across 6 items; 5 tools + 1 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 Management100
  • No destabilizing schema changes in the last 30 days.Pass
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 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 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
  • Supports UI / widget rendering.Pass
What we tested

Checks we ran (14)

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

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.

  • 11 Nov 26 0
    • Stability: 0.97 → pass security
  • 10 Nov 26 0
    • Stability: pass → 0.97 functional
  • 9 Nov 26 0
    • Stability: 0.97 → pass security
  • 8 Nov 26 0
    • Stability: pass → 0.97 functional
  • 7 Nov 26 0
    • Endpoint reachability: unreachable → reachable ▲ functional
  • 6 Nov 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
  • 5 Nov 26 0
    • Endpoint reachability: reachable → unreachable ▼ security
    • HSTS header: fail → unverified ▼ security
    • Stability: pass → unverified ▼ security
    • Authorization: partial → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • TLS certificate: pass → unverified ▼ security
    • Transport: pass → fail ▼ security
    • Schema quality: 100 → unverified ▼ functional
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
  • 24 Oct 26 0
    • Stability: 0.97 → pass security
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://mcp.hardcopylabs.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcp.hardcopylabs.com CN=YE1,O=Let's Encrypt,C=US 22 Oct 2026 20 Jan 2027 ECDSA 256 ECDSA-SHA384 5e0da95286f4e0b1e551a492b59cd8a186f
SANs: mcp.hardcopylabs.com
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 mcp.hardcopylabs.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
hardcopylabs.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

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.hardcopylabs.com/mcp Verified 200
http (plaintext) http://mcp.hardcopylabs.com/mcp HTTPS enforced 301 https://mcp.hardcopylabs.com/mcp
MCP tools · 5 exposed · ~2,094 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
check_job_status ~84

Look up the current status of a print job (submitted, approved, printing, QC, shipped) and its UPS tracking number once shipped. Use when the user asks about an order they placed with HardCopy Labs.

NameTypeReqDescription
job_idstringyesThe order id, like hc-1a2b3c4d, returned by submit_print_job.
NameTypeReqDescription
resultstringyes–

No examples provided.

preview_print_order ~541

MANDATORY before creating any order or checkout, including reorders. Render exact validated geometry and quote the whole order. Display EVERY returned part image with name, dimensions, material/color, quantity, notes and total to the buyer. The in-chat card shows images where supported; otherwise embed image_url values or give viewer_url and ask the buyer to review there. Never substitute an AI illustration, or describe unshown images as reviewed. Ask for explicit buyer confirmation of this version only after presenting the preview. Changes require a new preview and new confirmation; pass replaces_preview_id to revoke the old preview. Preview failure blocks ordering. After confirmation call submit_print_job (or reorder_print_job) using preview_id, preview_version, buyer_confirmed=true and shipping/contact details; do not resend models or option overrides. Preview generation and viewing never create an order. Separate parts are displayed individually, not as an inferred assembly.

NameTypeReqDescription
color––Selected filament color. Default black for new models; omit to retain reorder colors.
job_namestring–Short order name shown with the preview.
material––PLA or PETG. Default PLA for new models; omit to retain reorder materials.
notesstring–Operator instructions to show and bind to this preview; changes require a new preview.
openscad_sourcestring–OpenSCAD source in millimeters. Rendered and validated before preview; never an illustrative AI image.
parts––The WHOLE order, one entry per part. Use a model_id from earlier validation, an STL, or OpenSCAD. Each entry has its own name, material, color and quantity. Each part's quantity is capped by its own…
quantityinteger–How many identical copies. The totals cover all of them. Capped by how long the part takes to print, not a flat number -- a quick part allows many copies, a very large or slow one may allow as few as…
reorder_ofstring–Existing order ID to preview for reorder; omit new model inputs when using this.
replaces_preview_idstring–When revising an unplaced order, pass its previous preview id. It is invalidated even if the new render fails.
stl_base64string–The model as a base64-encoded STL file (binary or ASCII), in millimeters.
NameTypeReqDescription
resultstringyes–

No examples provided.

reorder_print_job ~454

A REORDER ALSO REQUIRES A NEW VISUAL PREVIEW AND BUYER CONFIRMATION. First call preview_print_order with reorder_of and any desired changes, show every image/options/price to the buyer, and obtain confirmation. Then call this with preview_id, preview_version and buyer_confirmed=true, without option overrides. Without a preview this returns a preview only; it never creates an order. In preview_print_order, quantity means complete sets for multi-part reorders; material/color overrides apply to every part. Omit overrides to preserve choices. Prices are recalculated. The previous order's geometry is reused without requesting a new upload. Shipping/contact details are never copied from the previous order; confirm the new address with the buyer. Orders cancelled by HardCopy Labs or still awaiting payment cannot be reordered. Returns a new job ID, total and payment link when payment is required, only after the new preview is confirmed.

NameTypeReqDescription
buyer_confirmedboolean–True ONLY after showing every preview image/options/price and receiving explicit buyer confirmation. Not proof of human viewing.
colorstring–Filament color. Leave empty to keep the earlier order's color.
contact_emailstring–The buyer's email, for the receipt and order updates. Not copied from the earlier order.
job_idstringyesThe id of the earlier order to copy, like hc-1a2b3c4d.
materialstring–pla or petg. Leave empty to keep the earlier order's material.
notes––Optional notes for the operator.
preview_idstring–The id returned by preview_print_order for the images shown to the buyer.
preview_versionstring–The exact preview version the buyer confirmed; changes require a new preview.
quantity––How many identical copies. Capped by print time, not a flat number; the totals cover all of them.
ship_tostringyesRecipient's full name and US street address, including city, state and ZIP. Not copied from the earlier order. We ship within the United States only.
NameTypeReqDescription
resultstringyes–

No examples provided.

submit_print_job ~592

Create an order ONLY AFTER preview_print_order, image display and buyer confirmation. First present every preview image (or the viewer fallback), dimensions, material/color, quantity and quote. Obtain explicit buyer confirmation for that preview version. Then send preview_id, preview_version, buyer_confirmed=true, job_name and shipping details ONLY; omit model/options fields. Any relevant change needs a new preview. Legacy model inputs without a preview return a preview and NEVER create an order. Set geometry, material, color, quantities and operator notes in preview_print_order. OpenSCAD is preferred for designs made in conversation; uploaded STL and cached model IDs are also supported there. One preview covers the whole multi-part order. Confirm the shipping address with the buyer. ship_to requires their full name and US address; contact_email is used for updates. This returns a job ID and total, plus a payment link when payment is required. The buyer pays in their own browser.

NameTypeReqDescription
buyer_confirmedboolean–True ONLY after showing every preview image/options/price and receiving explicit buyer confirmation. Not proof of human viewing.
color––Filament color, e.g. black or white.
contact_emailstring–The buyer's email, for the receipt and order updates.
job_namestringyesA short name for the item, shown on the order and the receipt, e.g. "Desk cable clip".
material––Print material: pla or petg.
notes––Optional notes for the operator, e.g. which face should look best.
openscad_sourcestring–OpenSCAD source for the model, in millimeters; rendered on our server. Preferred for models designed in the conversation. Give this or stl_base64, not both.
parts––The WHOLE order, one entry per part. Use a model_id from earlier validation, an STL, or OpenSCAD. Each entry has its own name, material, color and quantity. Each part's quantity is capped by its own…
preview_idstring–The id returned by preview_print_order for the images shown to the buyer.
preview_versionstring–The exact preview version the buyer confirmed; changes require a new preview.
quantity––How many identical copies. Capped by print time, not a flat number; the totals cover all of them.
ship_tostring–Required. Recipient's full name and US street address, including city, state and ZIP. We ship within the United States only.
stl_base64string–The model as a base64-encoded STL file, in millimeters. Give this or openscad_source, not both.
NameTypeReqDescription
resultstringyes–

No examples provided.

validate_stl ~423

Check whether a 3D model can be printed, before ordering. A text validation quote is NOT approval to order. Call preview_print_order next, show its exact model images/options/price to the buyer, then obtain confirmation. Use this when the user has an STL file (base64-encoded) and wants to know if it is printable, or as a pre-check before submit_print_job. Returns printability (watertight/manifold status), dimensions, which printers it fits on, and the total for each material: what submit_print_job will charge for this file, shipping included. If the user is designing an object in this conversation, generate the STL, then call this to confirm it can be manufactured. Pass quantity (default 1) when the user wants several copies, so the totals cover all of them. For multiple parts, pass the WHOLE order in parts with each material/color/quantity. Never add separate quotes: totals already include shipping and handling once. To keep payloads small, validate each STL first and reuse its model_id (24 hours). PLA and PETG are the only materials offered.

NameTypeReqDescription
parts––The WHOLE order, one entry per part. Use a model_id from earlier validation, an STL, or OpenSCAD. Each entry has its own name, material, color and quantity. Each part's quantity is capped by its own…
quantityinteger–How many identical copies. The totals cover all of them. Capped by how long the part takes to print, not a flat number -- a quick part allows many copies, a very large or slow one may allow as few as…
stl_base64string–The model as a base64-encoded STL file (binary or ASCII), in millimeters.
NameTypeReqDescription
resultstringyes–

No examples provided.

Install

How do I install the HardCopy Labs MCP server?

HardCopy Labs is a hosted endpoint at https://mcp.hardcopylabs.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 · mcp.hardcopylabs.com

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

What is the HardCopy Labs MCP server?

HardCopy Labs is an MCP server listed in the public MCP registry as com.hardcopylabs/hardcopy. Order real 3D prints from chat: send an STL or OpenSCAD model, see one price, get it by UPS. This page covers its hosted endpoint (https://mcp.hardcopylabs.com/mcp).

Is the HardCopy Labs MCP server safe to use?

HardCopy Labs scores 85 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 HardCopy Labs MCP server expose?

HardCopy Labs exposes 5 tools: preview_print_order, validate_stl, submit_print_job, check_job_status, reorder_print_job. Their descriptions and schemas cost roughly 2,094 tokens of context every time the server is loaded.

Does the HardCopy Labs MCP server require authentication?

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

Is the HardCopy Labs MCP server still maintained?

HardCopy Labs 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 HardCopy Labs MCP server?

VerifyMCP ran 14 checks on HardCopy Labs, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 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.