Atlas / MCP servers / lm203688 / roboparts

robopartsBLOCK

Name: roboparts
Author: lm203688

mcp/lm203688/roboparts

MCP server by lm203688 · cadquery · compatibility · embodied ai · Audited 2026-10-12

RoboParts — Vendor-neutral composition checker for embodied systems | 具身系统的组合校验层(开源、厂商中立)| 868 实体 / 20 品类 / ISO 9409-1 法兰判定 / 三态 fail-closed 裁决(能/不能/不知道)| MCP Server + 开放 API + GitHub Action

Verdict

BLOCK

Grade

Trust score

40 /100

Exposed tools

38 38r · 0w · 0d

Transport

stdio · streamable-http

License

MIT

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

RoboParts — vendor-neutral composition checker for embodied systems. 判定零件能否装配 / 共装 / 互换,输出可核验的三态结论(能 / 不能 / 不知道),并生成可 3D 打印的转接件。我们不卖零件,所以没有理由骗你选一个。

1. Project Overview

Name: RoboParts — 具身系统的组合校验层(Vendor-neutral composition checker for embodied systems)
Positioning: 面向开源机器人构建者的组合校验层。判定零件能否装配/共装/互换,输出可核验的三态结论(能/不能/不知道),并生成可打印转接件。开源、中立、可追溯。
English positioning: Vendor-neutral composition checker for embodied systems — decide whether parts can be assembled / co-mounted / interchanged, returning verifiable three-state verdicts (compatible / incompatible / unknown) and printing transfer adapters.
Why not a "part database": 数据只是载体,真正不可复制的是判定引擎(三态 fail-closed compose)+ 三条定理(T1/T2/T3)+ 40 项 CI 闸门 + 溯源纪律。
Domain: roboparts.cc
Live URL / 线上地址: https://roboparts.cc
线上地址(正式入口,外链一律指向此域): https://roboparts.cc
Preview domain / 预览域(Cloudflare Pages 默认域,非正式入口,勿对外引用): https://robotparts-924.pages.dev

Data volume / 数据量: 868 entities / 868 实体 (659 physical parts / 101 interface specs / 81 AI model software / 10 organizations / 17 market intelligence);Mechanical interface declaration rate 16.2% (81/500);Open-source components 325
Last updated / 最后更新: 2026-10-12

2. Core Goals

Modular accessories — standardized module parameter library, supporting filtering and combination by degrees of freedom / torque / size / protocol
Interface standardization — align with the national standard General Technical Requirements for Humanoid Robot Modularity, build a compatibility database
Protocol standardization — EtherCAT/CANopen/ROS2/MQTT protocol stack comparison, real-time performance benchmarks, cross-protocol bridging
Large-model industrialization — deployment hardware requirements and inference performance comparison for VLA models (RT-2/OpenVLA/π0/GR00T N1.

Read from source at commit 4f5798deb70eOBSERVED · 2026-10-12

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code

claude mcp add roboparts --env BAIDU_PUSH_TOKEN=${BAIDU_PUSH_TOKEN} --env CF_API_TOKEN=${CF_API_TOKEN} --env CLOUDFLARE_API_TOKEN=${CLOUDFLARE_API_TOKEN} --env GH_TOKEN=${GH_TOKEN} -- npx -y [email protected]

claude-desktop

{
  "mcpServers": {
    "roboparts": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "BAIDU_PUSH_TOKEN": "${BAIDU_PUSH_TOKEN}",
        "CF_API_TOKEN": "${CF_API_TOKEN}",
        "CLOUDFLARE_API_TOKEN": "${CLOUDFLARE_API_TOKEN}",
        "GH_TOKEN": "${GH_TOKEN}"
      }
    }
  }
}

Exposed tools (38)

38 read · 0 write · 0 destructive.

Tool	Risk	Description
`RoboParts`	read	厂商中立的机器人零部件兼容性数据层。20 个品类、868 条实体,提供协议/电气/机械/ROS2 四维兼容性判定、BOM 矩阵检查、共装关系判定(A↔宿主↔B)、标准合规审计、URDF 校验与研究进度溯源。既不生产也不转售任何零部件,兼容性结论基于厂商公开声明字段的规则推断,未声明维度显式标为 unknown。
`bom_compatibility_check`	read	对一组零部件(BOM,物料清单)做两两兼容性矩阵。输入已有条目 ID(可含开源贡献层 OSS-xxx),
`check_co_mount`	read	查询共装关系(第三种关系类型,三段 A↔宿主↔B):某个机器人本体
`check_compatibility`	read	判定两个零部件在 protocol(协议)/ electrical(电气)/ mechanical(机械)/ software(ROS2)四个维度的兼容性,
`compare_components`	read	并排对比 2~6 个零部件的关键参数(torque/speed/voltage/protocol/interface/weight/price),
`dialects_evaluate`	read	按领域方言对单个零部件做场景化评分。总分仅基于库内有证据的维度加权,无证据维度不计分(返回 null),不冒充 50 分。
`dialects_list`	read	列出可用的领域方言模板(人形/工业机械臂/灵巧手/移动机器人/科研教育),用于按应用场景评估零部件。
`explain_compose_frontier`	read	【研究层口径 · 与 check_compatibility 的四维不同】查询 RoboParts 三轴组合判定
`explain_connector_types`	read	【研究层口径】查询连接器取证与类型判据:已核实的连接器(针数/针序/供电)、
`explain_evidence_cohort`	read	【研究层口径】查询「最小可行同质集」取证判据:补哪一条数据最值、
`explain_evidence_mdv`	read	【研究层口径】查询边际声明价值(MDV):各轴未声明节点的零贡献率、
`export_bom`	read	从选定的零部件列表导出BOM(Bill of Materials)清单。计算总成本(USD+CNY),提供供应商建议和采购建议。
`get_behavior_evidence`	read	查询行为证据:开源 VLA 在真机上的 benchmark 成功率(引用论文/官方报告,
`get_body_binding`	read	查询开源 VLA → 机器人本体的绑定及其强度分档。
`get_component_detail`	read	按 ID 获取单个零部件的完整字段,包含 source_tier(数据来源等级)、confidence(置信度)、
`get_parameter_semantics`	read	获取参数口径规范:同一个 torque/speed 字段在不同厂商那里含义可能不同(库内 torque 出现 19 种口径、speed 37 种,
`get_research_progress`	read	查询「核心目标完成度」的可复现判据:把核心目标(脑×体×智做成机器可校验的
`get_robot_tool_side`	read	查询机器人本体的工具侧接口取证:工具法兰(ISO 9409-1 标号)、
`get_standard_audit`	read	返回标准登记表 ↔ 实体声明的自动交叉校验结果:哪些机械/总线声明能被已知标准集核实、
`lint_urdf`	read	对 URDF(Unified Robot Description Format)XML 文件做静态兼容性检查。
`recommend_for_application`	read	按应用场景推荐零部件组合,可选预算上限(USD)。返回各品类的候选项及推荐理由。
`review_compatibility`	read	对两个零部件做「多 Agent 质保复核」:Worker 层执行标准四维兼容性裁决(与 /api/compatibility 同一引擎),
`search_components`	read	搜索机器人零部件。可按品类、关键词筛选,返回匹配条目的摘要(id/name/category/manufacturer/关键规格/证据等级)。
`semantic_search`	read	用自然语言描述需求(如
`人形机器人场景`	read	适用于双足人形机器人的选型场景,关注关节自由度、力矩分布、平衡控制
`关节力矩匹配`	read	检查执行器力矩是否满足人形机器人关节需求
`协作机器人`	read	适用于人机协作的轻型机械臂
`实时控制支持`	read	检查控制器是否支持实时运动控制
`工业机械臂场景`	read	适用于工业协作机器人和传统工业机械臂,关注精度、负载、重复定位精度
`工业级人形`	read	适用于工业应用的大型人形机器人
`指尖力匹配`	read	检查执行器力是否满足抓取需求
`灵巧手场景`	read	适用于机器人灵巧手和末端执行器,关注指尖力、自由度、抓取能力
`科研教育场景`	read	适用于高校科研和教育机器人,关注可扩展性、文档、社区支持
`移动机器人场景`	read	适用于AMR、AGV等移动机器人,关注导航、避障、续航
`精度匹配`	read	检查传感器精度是否满足定位要求
`自由度匹配`	read	检查执行器数量是否满足自由度需求
`负载匹配`	read	检查执行器力矩是否满足负载需求
`轻量级人形`	read	适用于科研教育的小型人形机器人

Trust audit

BLOCKgrade F · trust 40/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	FAIL
L2	Instruction surface (what it tells the agent)	FAIL
L3	Class-specific surface	PASS
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (15 observation(s))
Network: declared (10 observation(s))
Shell: declared (11 observation(s))
Dependencies: not all pinned
Secrets in source: none-found

Findings (25)

HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95

scripts/verify_l136_injections.py:33

'exec(open(r"%s",encoding="utf-8").read().replace('

Why it matters. evaluates text as code

Fix. remove; use a parser or a dispatch table

HIGHFilesystem / path · fs.credential_store · CWE-22, CWE-59

functions/_middleware.js:186

/wp-|wordpress|\.env|\.git|\.svn|\.aws|\.ssh|id_rsa|phpmyadmin|xmlrpc|eval-stdin/i;