Skip to content

MadeCheck MCP server

Which MCP servers are MadeCheck's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-28

← Back to MadeCheck

Whose server it is
  • Registry namecom.madecheck/madecheckverified in the MCP registry

The registry name sits under madecheck.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools28
  • Server calls itselfcom.madecheck/madecheck
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 332 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: estimate landed cost of goods imported from China; check import requirements for a product before buying.
  • Checked on 6 of the 7 days it takes to judge reliability.

Once connected

  • For "estimate landed cost of goods imported from China", the likely first call is estimate_landed_cost.
  • For "check import requirements for a product before buying", the likely first call is list_import_requirements.
  • Keep approval on for revoke_signoff, send_order_pack_to_factory, pay_style_topup: they delete, send or pay without saying so.
  • create_order_pack, add_order_pack_material, send_order_pack_to_factory, cancel_order_pack, post_order_pack_message change data without a sign-in: anyone with the address can call them.
  • Parameters are untyped or undescribed in 28 of 28 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 6, the first on 2026-10-28
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring6 of the 7 daily checks it takes to print a share
  • Median first answer79 ms
  • Space in an agent's context≈ 4,767 tokensthe definitions of all its tools (28), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results0 of 28 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 28 of 28

What an agent can do with it

  • can do · estimate landed cost of goods imported from China
  • can do · check import requirements for a product before buying

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

  • Tools that delete, send or pay, marked as not destructive: revoke_signoff, send_order_pack_to_factory, pay_style_topup
  • Tools that change data, on a server that answers without a sign-in: create_order_pack, add_order_pack_material, send_order_pack_to_factory, cancel_order_pack, post_order_pack_message

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers28 tools · read 2026-10-28
  • estimate_landed_cost

    Estimate landed cost. Estimate a shipment total from hts_code or product, total fob_usd and quantity; returns duty lines, fees and total/per-unit cents with tax-date notes. Pass hts_code for a calculation; with only product you get a…

  • list_import_requirements

    List import requirements. List category requirements for product, with optional category and for_children; returns applicable requirements, citations, labels and testing notes. For a reliable result, pass category, one of: toys_children…

  • lookup_factory

    Look up factory. Find a company by query (name, registration code or store link) and request_id; returns found, its evidence-backed dossier and charged_cents. charges credits. 工厂档案。用 query 中的公司名称、登记代码或店铺链接及 request_id 查工厂;返回 found、带证据的档案及…

  • create_order_pack

    Create order pack. Open an order pack using title, style_count, materials and request_id; returns a queued publication, order_pack_id, version and charged_cents. charges credits. 开订单包。用 title、style_count、materials 和 request_id…

  • add_order_pack_material

    Add order pack material. Add text or uploaded documents in materials to order_pack_id with request_id; returns the queued material publication and its target version. charges credits. 加材料(成员侧)。用 order_pack_id、materials 和 request_id…

  • answer_order_pack_lines

    Answer order pack lines. Submit factory answers for line_id entries at the current order_pack_id/version, optionally new_lines; returns a queued answer publication and version. 工厂答复。按 order_pack_id、当前 version 和 answers 中的 line_id…

  • get_order_pack

    Get order pack. Read order_pack_id at an optional published version; returns pack details and lines with derived signoffs, limited to the factory view for company callers. 看订单包。按 order_pack_id 及可选已出版 version…

  • list_order_packs

    List order packs. List the caller owner's order packs using optional status, limit and cursor; returns visible packs and next_cursor for the next page. 列出订单包。用可选 status、limit 和 cursor 列出本人所属的订单包;返回可见订单包及下一页 next_cursor。

  • sign_order_pack_lines

    Sign order pack lines. Sign lines identified by line_id and the seen value_sha256 in order_pack_id; returns completion or a pending_action_id awaiting the person. requires the member's own approval. 签认若干行。按 order_pack_id 及 lines 中的…

  • revoke_signoff

    Revoke signoff. Revoke the caller side's active signoffs for order_pack_id and lines of line_id before deposit; returns completion after pack state is recalculated. not available to AI agents. 撤回签认(定金前)。定金前按 order_pack_id 和 lines 中的…

  • send_order_pack_to_factory

    Send order pack to factory. Prepare factory access to a published order_pack_id using channel=copy_link and request_id; returns link_ready or a pending_action_id, without the link itself. requires the member's own approval. 给工厂发链接。用…

  • mark_deposit_paid

    Mark deposit paid. Freeze the current order_pack_id/version after deposit payment with request_id; returns completion or a pending_action_id awaiting the member. requires the member's own approval. 定金已付,锁版。用 order_pack_id、当前 version 和…

  • decline_order_pack

    Decline order pack. Decline a factory order before deposit using order_pack_id, reason_zh and request_id; returns completion or a pending_action_id for the factory rep. requires the factory rep's own approval. 工厂拒单。工厂在定金前用…

  • cancel_order_pack

    Cancel order pack. Cancel order_pack_id before deposit using request_id; returns completion or a pending_action_id, with refunds governed by first publication. requires the member's own approval. 成员作废。定金前用 order_pack_id 和 request_id…

  • post_order_pack_message

    Post order pack message. Post body to order_pack_id with optional line_id and visible_to; returns message_id or a pending_action_id when an AI requests factory-visible text. messages an AI sends for the factory to see require approval…

  • list_order_pack_messages

    List order pack messages. Read messages for order_pack_id using limit and cursor; returns messages and next_cursor, with company callers seeing only both-side messages. 看留言。按 order_pack_id、limit 和 cursor 看留言;返回留言及 next_cursor,公司侧只看双方可见留言。

  • request_compliance_check

    Request compliance check. Request a quote for product and optional category, materials and order_pack_id with request_id; returns compliance_case_id, quoted_cents and items_preview. 申请合规办理(只报价)。用 product、request_id 及可选…

  • accept_compliance_quote

    Accept compliance quote. Accept the quoted compliance_case_id using request_id and available credits; returns case completion state and charged_cents after payment. charges credits. 接受报价。用 compliance_case_id、request_id 和可用额度接受合规报价;返回受理状态及…

  • add_compliance_material

    Add compliance material. Add text or completed documents in materials to an accepted or in-progress compliance_case_id using request_id and optional note (up to 2000 characters); returns done without charging credits. 补充合规材料。用…

  • get_compliance_check

    Get compliance check. Read the caller member's compliance_case_id; returns the case status, quoted_cents and its requirements with supporting citations. 看合规办理。按 compliance_case_id 看本成员的合规办理;返回状态、quoted_cents 和带出处的要求。

  • list_compliance_checks

    List compliance checks. List the caller member's compliance cases using limit and cursor; returns cases and next_cursor for pagination. 列出合规办理。用 limit 和 cursor 列出本成员的合规办理;返回办理列表及下一页 next_cursor。

  • start_document_upload

    Start document upload. Register kind, filename and sha256 with request_id and optional order_pack_id; returns document_id and a one-use upload_url for a raw-byte PUT. 开始上传。用 kind、filename、sha256、request_id 及可选 order_pack_id 开始上传;返回…

  • finish_document_upload

    Finish document upload. Finish a previously uploaded document_id with request_id after verifying its stored hash; returns document_id and done state. 上传完成。用 document_id 和 request_id 完成上传,核对已存文件哈希;返回 document_id 和 done 状态。

  • get_credit_balance

    Get credit balance. Read member credit balance and recent transactions using optional limit and cursor; returns balance_cents, transactions and next_cursor. 查额度。用可选 limit 和 cursor 查成员额度及近期变动;返回 balance_cents、transactions 和 next_cursor。

  • get_buy_credits_link

    Get buy credits link. Get the payment URL at https://madecheck.com/credits/buy, optionally prefilled with positive amount_cents; returns url and available to show whether credit sales are open. 拿买额度链接。用可选的正整数 amount_cents 取得…

  • list_pending_actions

    List pending actions. List awaiting actions using limit and cursor; returns actions and next_cursor, restricted to the AI requester or the person's own owner. 列出等本人点的请求。用 limit 和 cursor 列出待本人点的请求;返回 actions 和 next_cursor,AI…

  • decide_pending_action

    Decide pending action. Decide pending_action_id with decision=approve or reject and request_id as the person; returns the decision or executed action result after current-value checks. not available to AI agents. 处理待本人点的请求。本人用…

  • pay_style_topup

    Pay style topup. Pay the pending style-tier difference for order_pack_id using request_id; returns completion with charged_cents, or a pending_action_id for an AI. charges credits. requires the member's own approval. 付款数补差。用 order_pack_id…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "madecheck": {
      "type": "http",
      "url": "https://mcp.madecheck.com/v1"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http madecheck https://mcp.madecheck.com/v1

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.madecheck.com/v1 as a custom connector in the settings.

OpenAPI spec

25 paths, read 2026-10-28. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.