medxpert-ortho-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@medxpert-ortho-mcp find a lab in Shanghai for knee implant fatigue testing"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
medxpert-ortho-mcp · Orthopedic device testing connector
mcp-name: io.github.zhaoxinghua09-cell/medxpert-ortho-mcp
English first, Chinese below.
An MCP server with 8 tools for orthopedic device testing work: lab matching, quotation estimation, UDI checks, dual-temporal standards lookup, class/path judgment trees, region routes, registration timelines and gap reports. Offline, standard library only, zero dependencies.
It exists because four MedXpert expert packs (medxpert-standards, medical-device-reg-translator,
medical-device-testing-link, med-device-compliance-toolkit) had been referencing a connector called
medxpert-ortho-mcp that was never built. This is that connector, built.
What is real and what is sample
Aspect | Status |
The server, the 8 tools, the protocol layer | Real. Implemented, unit-tested, published to PyPI and to the official MCP Registry |
The datasets shipped in | Sample. Invented labs, invented prices, invented UDI-DIs. Illustrative only |
Every tool result | Carries |
The bundled data is not an accreditation directory, not a price commitment, and not
a regulatory conclusion. Point ORTHO_DATA_DIR at your own JSON files to use real evidence.
Related MCP server: @nomos/medxpert/reg-connector
Data that does not fit fails loudly
A wrong data path used to be the most dangerous state this server could be in: the tools would keep
answering, from sample data, and sample_data: true was the only clue. That is a silent failure with
a regulatory conclusion on the far end of it, so it is now an error:
Situation | Behaviour |
| The call fails with the path in the message. It never falls back to samples |
A required dataset file missing | Fails, naming the file and the directory in use |
Malformed JSON | Fails, naming file, line and column |
JSON valid but top-level keys wrong | Fails, listing the keys that are required |
Structurally bad content (orphan lab reference, 13-digit UDI, unknown status, empty phase list) | Reported by the check below, per file and per cross-check |
Check your own data before relying on it:
ORTHO_DATA_DIR=/path/to/your/datasets python -m medxpert_ortho.server --validate-dataIt prints a structured report, DATA CHECK: PASS or FAIL, and exits 1 on failure — so it can be
a CI step rather than a ritual.
Run
uvx medxpert-ortho-mcp # stdio MCP server
python -m medxpert_ortho.server --selftest # offline self-test, no host needed
python -m medxpert_ortho.server --validate-data # check ORTHO_DATA_DIR (or the bundled samples)MCP host configuration:
{"mcpServers": {"medxpert-ortho-mcp": {"command": "uvx", "args": ["medxpert-ortho-mcp"]}}}Custom data directory:
{"mcpServers": {"medxpert-ortho-mcp": {
"command": "uvx", "args": ["medxpert-ortho-mcp"],
"env": {"ORTHO_DATA_DIR": "/path/to/your/datasets"}}}}Tools
Tool | What it does | Honest limit |
| Ranks labs by capability keyword, region and device description | Sample data has 3 labs and a few capability items |
| Price range by lab and scope, total estimated by quantity (>included samples +12%) | Prices are illustrative; not a commercial offer |
| 14-digit UDI-DI lookup, returns class / sterile / single-use | Misses are explained as sample-data scope, not proof of absence |
| Keyword search with | Status fields are demo logic; verify against the official current version |
| Step-by-step classification / route questions | A demo tree, not a review decision |
| Authority, route note and required documents per region | Sample routes only for CN / CN-JS / CN-SH |
| Expands relative days into calendar dates, marks completed / in_progress / not_started, flags overdue | Durations are illustrative; official clocks start at acceptance |
| Compares present documents against the required checklist | Checklist is sample data |
Design notes
Zero dependencies. JSON-RPC 2.0 over stdin/stdout, implemented with the standard library only. No network calls at runtime; nothing leaves the machine.
Provenance in every answer. A tool that cannot say whether it answered from sample data or from your own data is a tool you cannot audit, so every result says which.
Mismatch is reported, not smoothed over. A UDI miss says "sample scope", a tree miss lists what trees exist, an empty lab match returns a hint rather than an empty success.
Bad input is an error, not a quiet fallback. See above: the server will not answer from samples while your data path is broken. The check is also runnable as
--validate-datawith a non-zero exit.
Gate
.github/workflows/ci.yml runs the unit tests and tools/version_gate.py, which checks
version consistency across pyproject.toml, __init__.py, server.json and the declared tool
count, and reports how many uses: references are pinned to full SHAs.
medxpert-ortho-mcp · 骨科器械检测对接连接器
先英后中。
一个 8 工具的 MCP server,用于骨科器械检测对接:机构匹配、报价估算、UDI 校验、双时态标准检索、 分类/路径判定树、地区路径、注册时间轴、缺口报告。离线、仅标准库、零依赖。
它存在的理由:四个 MedXpert 专家包(medxpert-standards、medical-device-reg-translator、
medical-device-testing-link、med-device-compliance-toolkit)从 2026 年起一直引用一个叫
medxpert-ortho-mcp 的连接器,而那个连接器从未被造出来。这就是它,现在有了。
哪些是真的,哪些是示例
方面 | 状态 |
服务本身、8 个工具、协议层 | 真的。 已实现、有单元测试、已发布到 PyPI 与官方 MCP Registry |
| 示例。 虚构机构、虚构价格、虚构 UDI-DI,仅供演示 |
每个工具返回值 | 只要没设 |
包内数据不是资质目录、不是报价承诺、不是法规结论。要用于真实工作,把
ORTHO_DATA_DIR 指向你自己的 JSON 数据目录。
数据不合规就报错,不静默降级
数据路径写错,曾是这台服务最危险的状态:工具照常作答,用示例数据答,唯一线索只有一个
sample_data: true。这是会一路传导到法规结论的静默失败,所以现在改成报错:
情形 | 行为 |
| 调用直接失败,错误信息里带路径;绝不退回示例数据 |
必需的数据集文件缺失 | 失败,并指出文件名与当前数据目录 |
JSON 语法错 | 失败,并指出文件、行、列 |
JSON 合法但顶层键不对 | 失败,并列出必需的顶层键 |
结构性问题(报价指向不存在的机构、13 位 UDI、非法 status、阶段为空) | 由下面的体检逐文件、逐交叉项报出 |
用自己的数据之前先体检:
ORTHO_DATA_DIR=/path/to/your/datasets python -m medxpert_ortho.server --validate-data输出结构化报告,末行 DATA CHECK: PASS 或 FAIL,失败时退出码 1——因此它可以进 CI,
而不只是一次仪式。
运行
uvx medxpert-ortho-mcp # 起 stdio MCP 服务
python -m medxpert_ortho.server --selftest # 离线自测,不需要宿主
python -m medxpert_ortho.server --validate-data # 体检 ORTHO_DATA_DIR(或包内示例)工具与诚实的边界
工具 | 做什么 | 边界 |
| 按能力关键词、地区、器械描述给机构打分 | 示例数据仅 3 家机构、少数能力项 |
| 按机构与能力项给价格区间,超出含样量 +12% | 价格为演示值,不构成商务报价 |
| 14 位 UDI-DI 查表,回出分类/无菌/一次性 | 未命中会说明是示例范围,不是"不存在"的证据 |
| 关键词检索 + | 状态字段为演示逻辑,以官方现行版为准 |
| 逐步问答式分类/路径判定 | 演示结构,不是审评结论 |
| 受理机关、路径说明、必备材料 | 仅 CN / CN-JS / CN-SH 三条示例路径 |
| 相对天数展开成日历,标 completed / in_progress / not_started 与逾期 | 天数为示例;官方时限自受理起算 |
| 已具备材料对照必备清单,报缺口与完整度 | 清单为示例数据 |
门禁
ci.yml 跑单元测试 + tools/version_gate.py:核对 pyproject.toml、__init__.py、server.json
与声明的工具数是否一致,并自报 uses: 有多少处钉了完整 SHA。
Available Tools
8 toolscalc_quoteA
按机构与能力项取报价区间并按数量估算总额(含超出含样量加价规则)。价格是示例区间,不构成商务承诺。
Inputs: scope (required), lab_id (required), quantity.
check_timelineB
把相对天数展开成日历日期,并按 as_of 标出 completed/in_progress/not_started 与逾期未启动项。
Inputs: as_of, region, procedure, start_date.
check_udiA
校验 14 位 UDI-DI 并回出分类/无菌/一次性属性。未命中会说明示例数据范围,不代表真实数据库无此编号。
Inputs: udi_di (required).
find_judgment_treeB
取分类/路径判定树(逐步问答结构)。演示结构,最终以分类目录与界定结论为准。
Inputs: region, procedure.
get_region_pathB
取地区路径:受理机关、路径说明与该程序的必备材料清单。
Inputs: region (required), procedure.
match_labsA
按能力关键词 / 地区 / 器械描述给检测机构打分排序。例:scope_keyword='力学疲劳'。返回命中能力项与联系方式;示例数据仅 3 家机构。
Inputs: limit, device, region, scope_keyword.
query_standardA
按关键词查标准,并可带 as_of 做双时态判定:该日是否已生效、是否已被替代。
Inputs: keyword (required), as_of.
report_gapB
对照必备材料清单报缺口:给已具备材料名列表,返回缺失项与完整度。
Inputs: present (required), procedure.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool targets a distinct object: lab matching, quoting, UDI validation, standards lookup, decision trees, regional paths, timeline expansion, and material gap reporting. The only mild overlaps are match_labs/calc_quote (both lab-centric) and find_judgment_tree/get_region_path (both pathway lookups), but the descriptions make the split clear enough that an agent can pick correctly.
All eight names are snake_case verb_noun pairs (match_labs, calc_quote, check_udi, query_standard, find_judgment_tree, get_region_path, check_timeline, report_gap) with a predictable noun following the action. No mixed casing or bare-noun outliers.
Eight tools sit squarely in the well-scoped 3-15 range, and each maps to a separable step of the orthopaedic device regulatory workflow (classify, test, quote, submit, track, gap-check). Nothing appears redundant or padded.
The surface covers the main journey: classification/decision tree, standards, regional path and required materials, lab matching, quoting, UDI attributes, timeline status, and gap analysis, so core workflows have no dead ends. Minor gaps remain: no tool to fetch a single lab's detail by ID, no full standard text retrieval, and no consolidated submission-plan/export step. Sample-data caveats in the descriptions also limit real-world coverage.
Maintenance
Related MCP Connectors
FDA 510(k)/PMA/De Novo, GUDID, recall and EUDAMED device and certificate data. Read-only, no login.
Citation-backed regulatory intelligence tools for explicit multi-jurisdiction packs
China medical-device Unique Device Identification (UDI) register, served (fleet #3410).
31 stateless B2B tools for KYB, OFAC sanctions, SEC EDGAR, CISA CVEs, FDA, tenders & tax audits.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables classification of medical devices, IVDs, and AI/ML SaMD under EU MDR and IVDR regulations.MIT
- AlicenseNot gradedqualityBmaintenanceEnables local read-only retrieval and search across 27 global medical device regulatory knowledge hubs (NMPA/FDA/MDR/PMDA etc.) using four MCP tools, with zero credentials and no external network calls.1Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables read-only local retrieval of medical-device and orthopedic standards via MCP tools, supporting searches by standard number, name, region, committee, topic, official links, and related regulations without network access or credentials.1Apache 2.0
- AlicenseAqualityBmaintenanceLook up EU HS chapters and headings, read listing requirements for 12 commerce channels, and screen product copy for environmental claims in four languages. All three tools run offline and are read-only.3MIT