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.

Customs Declaration Consistency

NPM · DSH-CUSTOMS-MCP

Read-only MCP server that checks a Chinese customs declaration ledger for internal inconsistency.

Available components

+3 this week 69 Trust /100

Last scanned (11 hours ago)

Scores higher than 37% of npm servers

Category Finance and Payments

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency19
Schema Quality & AI Usability74
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 754 tokens (~188/item across 4 items; 4 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 Management53
  • Stability observed for 16 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
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 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
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
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.

  • 3 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

  • 1 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

  • 30 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

  • 28 Oct 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.

  • 26 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 25 Oct 26 +2
    • Stability: unverified → 0.17 ▲ functional
  • 21 Oct 26 +15
    • Malware scan: unverified → pass ▲ security
  • 20 Oct 26 47

    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 5 Nov 2026 · Analysed npm/dsh-customs-mcp@0.1.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 4 exposed · ~754 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
customs_check ~312

Run the customs declaration rule pack over a declaration ledger and return the findings as a Markdown report. The input is a JSON or YAML table: one row per document line, with columns such as 品名 (description), 商品编号 (HS code), 币制 (currency), 毛重/净重 (gross/net weight), 申报日期 (declaration date) and 总价 (total value). Call customs_schema for the exact field names and their aliases. The report lists only literal differences from the declared checks — an HS code that is not ten digits, a currency that is not a 3-letter code, gross weight below net weight, a duplicated document number, a date that does not parse or is in the future, an unfilled placeholder. Each finding carries the clause it rests on, or states that the clause text was not obtained. It does NOT decide whether a declaration is correct, whether goods are misclassified, or whether duty is owed. It performs no writes and needs no credentials. Read the "未执行的检查" (checks not executed) section at the end: it names every rule that did not run and why, and a report is only as complete as that list allows.

NameTypeReqDescription
materialstringyesThe ledger as JSON or YAML text. Either an object with a `rows` array, or a bare array of row objects.
onlyRulesarray–Run only these rule ids, e.g. ["CD-002"]. Omit to run the whole pack.

No output schema declared.

No examples provided.

customs_read_docx ~220

Extract text from a .docx file so it can be turned into a ledger for customs_check. Paragraphs come out one per line; table rows come out as "| a | b | c |" lines. Merged cells are marked "↔", meaning "this cell is merged with the one to its left and holds no value of its own" — do not read it as a missing value. A vertically merged cell repeats the value above it, which is what a reader of the document sees. Reads exactly the one path given, opens it read-only, and refuses anything larger than 20 MB. No other file is touched, no network is used, nothing is written. Only a path ending in .docx is accepted: legacy .doc/.wps are a different binary format and PDF is not parsed on purpose — a PDF table loses its cell structure, and guessing it produces a ledger that is wrong in ways the check cannot detect.

NameTypeReqDescription
pathstringyesAbsolute or working-directory-relative path to the .docx file.

No output schema declared.

No examples provided.

customs_rulebook ~134

Return every rule in the pack: id, title, severity, the basis kind (direct clause / derived from principle / local configuration), the document and clause it cites, and whether the pack actually holds the verbatim clause text. The `coverage` object states how many rules carry a verbatim clause and how many record that the clause was not obtained, so a reader can weigh the report instead of trusting it. This is the answer to "how much of this is actually backed by a quoted regulation" — the number is computed from the pack, not asserted. Read-only, no parameters, no network, no writes.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

customs_schema ~88

Return the column contract for customs_check: the accepted field names, every alias each field answers to (for example 品名 / goodsName, 币制 / currency), and the header-level fields. Call this first when assembling a ledger, because a column name the reader does not recognise is silently dropped and the corresponding rule then reports nothing. Read-only, no parameters, no network, no writes.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Install

How do I install the Customs Declaration Consistency MCP server?

Customs Declaration Consistency runs locally as an npm package, launched with npx -y dsh-customs-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · dsh-customs-mcp

# add to Claude Code
claude mcp add perrylink-dsh-customs -- npx -y dsh-customs-mcp
Common questions

What is the Customs Declaration Consistency MCP server?

Customs Declaration Consistency is an MCP server listed in the public MCP registry as io.github.PerryLink/dsh-customs. Read-only MCP server that checks a Chinese customs declaration ledger for internal inconsistency. This page covers its npm package (dsh-customs-mcp).

Is the Customs Declaration Consistency MCP server safe to use?

Customs Declaration Consistency scores 69 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. 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 Customs Declaration Consistency MCP server expose?

Customs Declaration Consistency exposes 4 tools: customs_check, customs_read_docx, customs_schema, customs_rulebook. Their descriptions and schemas cost roughly 754 tokens of context every time the server is loaded.

Is the Customs Declaration Consistency MCP server still maintained?

Customs Declaration Consistency is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Customs Declaration Consistency MCP server under?

Customs Declaration Consistency declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.