{"name":"cc.roboparts/roboparts","title":"RoboParts 机器人零部件兼容性","url":"https://roboparts.cc/mcp","host":"roboparts.cc","read_at":"2026-11-10T15:26:19.326217+00:00","grade":"A","score":100,"capped":null,"graded":true,"pending_second_read":[],"counts":{"error":0,"warning":0,"info":1},"findings":[{"rule":"mcp-version-differs","severity":"info","message":"The version it reports differs from its newest registry entry. It reports 1.2.0; the registry lists 1.1.1.","fix":"","where":[],"count":0}],"handshake":{"answered":true,"mcp":true,"era":"handshake","protocol_version":"2025-11-25","server_info":{"name":"roboparts","version":"1.2.0","title":"RoboParts 机器人零部件兼容性"},"capabilities":["resources","tools"]},"sign_in":null,"tools":[{"name":"search_components","title":null,"description":"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）。覆盖执行器、传感器、芯片、通信协议、接口、机器人平台、具身智能模型等 20 个品类。库存实时口径（总数/可选型/已隔离）见 initialize 的 instructions 或 GET /mcp 的 dataset 字段 —— 此处不写死数字，避免文案与真实库存漂移。","read_only":null,"destructive":null,"inputs":["category","keyword","limit","include_market_intelligence"],"required":[],"price_stated_usd":null},{"name":"get_component_detail","title":null,"description":"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）、data_quality 与 mechanical_interface 等元数据。用于在做出采购/设计决策前核对证据强度。","read_only":null,"destructive":null,"inputs":["id"],"required":["id"],"price_stated_usd":null},{"name":"check_compatibility","title":null,"description":"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，返回逐维结论、总体判定与置信说明。注意：结论基于厂商公开声明字段做规则推断，非实验室实测；厂商未声明的维度记为\"无法判定\"，既不计入兼容也不计入不兼容。","read_only":null,"destructive":null,"inputs":["component1_id","component2_id"],"required":["component1_id","component2_id"],"price_stated_usd":null},{"name":"compare_components","title":null,"description":"并排对比 2~6 个零部件的关键参数（torque/speed/voltage/protocol/interface/weight/price），相同值自动标注，替代为同一目的连发多次 get_component_detail。缺失字段以 null 呈现，不代表不支持该特性；跨厂商数值比较请配合 get_parameter_semantics。","read_only":null,"destructive":null,"inputs":["ids"],"required":["ids"],"price_stated_usd":null},{"name":"recommend_for_application","title":null,"description":"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。这是基于库内字段的启发式筛选，不构成工程选型意见，最终仍需核对厂商原始数据手册。","read_only":null,"destructive":null,"inputs":["application","budget","count"],"required":["application"],"price_stated_usd":null},{"name":"get_parameter_semantics","title":null,"description":"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，甚至混入 Gbps 与 rad/s）。本工具返回物理红线、单位换算、可比性分级与向厂商问询的清单，用于判断两份参数表到底能不能直接比较。","read_only":null,"destructive":null,"inputs":[],"required":[],"price_stated_usd":null},{"name":"bom_compatibility_check","title":null,"description":"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），返回每个组合在 protocol/electrical/mechanical/software 四维的判定与理由。判定基于厂商公开声明字段的规则推断而非实测；未声明维度记为无法判定，不会为了填满矩阵而编造结论。返回的 verdict_reason 才是结论依据，overall_compatible=null 表示\"证据不足\"，不等于不兼容。","read_only":null,"destructive":null,"inputs":["component_ids"],"required":["component_ids"],"price_stated_usd":null},{"name":"semantic_search","title":null,"description":"用自然语言描述需求（如\"人形机器人髋部高扭矩电机\"）做语义召回，返回最相近的零部件。语义索引由离线哈希 TF-IDF 向量（构建时预计算、零外发、零外部模型）在当前全量实体上生成，是兼容性判定之外的\"发现\"通道：当你不确定零件的确切型号或参数名时，用它比关键词子串匹配更稳。索引不可用时自动降级为关键词检索，并明确告知。","read_only":null,"destructive":null,"inputs":["query","k"],"required":["query"],"price_stated_usd":null},{"name":"get_standard_audit","title":null,"description":"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、哪些声明的编码不在已知指定集中（无法核实），以及登记表缺口与行业标准覆盖情况。这是数据质量自检，不是兼容性裁决；其作用是指出\"声明了但出处存疑\"的条目，供人工补全证据。","read_only":null,"destructive":null,"inputs":["scope"],"required":[],"price_stated_usd":null},{"name":"review_compatibility","title":null,"description":"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），Governor 层独立复核结论——按证据强度给出 L0–L3 风险分级、在证据不足 2 条时把\"兼容\"降级为\"需人工确认\"、对无法判定项显式列出缺失证据段。返回四维细节 + 证据契约 + governor_review。只读、免鉴权。","read_only":null,"destructive":null,"inputs":["component1_id","component2_id"],"required":["component1_id","component2_id"],"price_stated_usd":null},{"name":"lint_urdf","title":null,"description":"对 URDF（Unified Robot Description Format）XML 文件做静态兼容性检查。返回结构化 JSON 报告，含 severity（error/warning/info）、issues 数组、summary 与 stats。检查 10 类问题：XML 解析错误、缺失根 link、关节限位缺失、关节类型非法、重复 link 名、运动学树循环、缺少 ROS 工业标准帧（flange/tool0/base）、缺少 origin、缺少 inertial 数据、mesh 路径问题。只读、免鉴权。适用于上传 URDF 到 RoboParts 前做兼容性预检。","read_only":null,"destructive":null,"inputs":["urdf_xml","check_level"],"required":["urdf_xml"],"price_stated_usd":null},{"name":"explain_compose_frontier","title":null,"description":"【研究层口径 · 与 check_compatibility 的四维不同】查询 RoboParts 三轴组合判定（mechanical 机械 / electrical 电气 / signal 信号角色）的现算结论：整体 composed/type_error/unknown、逐轴裁决与理由，以及「为什么 composed 通常为 0」的归因（L1 跨角色 → L2 机械可判定 → L3 全轴可判定的三层分解）。适合回答「这两个零件为什么判为 type_error」「哪些配对能真的装起来」「composed=0 是数据缺口还是关系类型问题」。只读、免鉴权。**注意口径差异**：本工具用 signal 角色互补（执行器↔传感器），check_compatibility 用 protocol 总线 + ROS2 支持，两者维度不同不可混用。","read_only":null,"destructive":null,"inputs":["component1_id","component2_id"],"required":[],"price_stated_usd":null},{"name":"explain_evidence_cohort","title":null,"description":"【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、为什么单条声明的边际收益为 0、以及应按缺口画像批量取证的顺序。适合回答「取证该从哪开始」「补机械声明率有没有用」「K=2 是什么意思」。只读、免鉴权。","read_only":null,"destructive":null,"inputs":[],"required":[],"price_stated_usd":null},{"name":"explain_evidence_mdv","title":null,"description":"【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、哪些取证方向边际收益恒为 0、以及瓶颈轴是哪个。适合回答「补哪个轴最划算」「某个轴还有取证价值吗」。只读、免鉴权。口径与 check_compatibility 不同，不可混用。","read_only":null,"destructive":null,"inputs":[],"required":[],"price_stated_usd":null},{"name":"explain_connector_types","title":null,"description":"【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）、「同族不同变体」的不可互插案例，以及 (family, pins, pinout) 三元组判据。适合回答「这两个连接器能不能互插」「同为 M8 为什么判不兼容」「pinout 为 null 是什么意思」。只读、免鉴权。","read_only":null,"destructive":null,"inputs":[],"required":[],"price_stated_usd":null},{"name":"get_research_progress","title":null,"description":"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组合 + 全链路可溯源）拆成四个维度的分项，每项给出分子/分母/口径/剩余缺口，并报出门控与朴素两个口径的加权完成度。适合回答「这个项目做到什么程度了」「核心目标完成了几成」「composed 为什么是 0」。只读、免鉴权。★ 口径警告：这是**一个口径**下的数字，不是客观测量；权重可争议；且采用**门控口径**——核心判据（composed）为 0 时 body 维记 0，因为「判定基础设施建成」不等于「组合成立」。","read_only":null,"destructive":null,"inputs":[],"required":[],"price_stated_usd":null},{"name":"check_co_mount","title":null,"description":"查询**共装**关系（第三种关系类型，三段 A↔宿主↔B）：某个机器人本体能否同时装下两个器件（典型问题：「这台 UR5e 能同时装夹爪和六轴力传感器吗」）。与 check_compatibility 的区别：后者判「A 能不能插进 B」（二段互插），本工具判「A 和 B 能不能同时挂在同一台机器人的工具侧」。★ 三段判据：机械同型 + 宿主工具侧位数预算 + 信号角色互补。port_exhausted 表示「**装不下**（工程约束，如需转接/换本体）」，与 unknown（「数据不足，不知道」）严格区分。★ 参数：传 host+a+b 得单对裁决（附证据链）；只传 host 得该宿主的单件可装性 + 工具侧取证；不传参得全层摘要（含关系语义与示例）。只读、免鉴权。返回含 caliber 字段，口径与 check_compatibility 不同、不可混用。","read_only":null,"destructive":null,"inputs":["host","a","b"],"required":[],"price_stated_usd":null},{"name":"get_robot_tool_side","title":null,"description":"查询机器人本体的**工具侧接口取证**：工具法兰（ISO 9409-1 标号）、工具 I/O 位数、连接器型号与承载信号。适合回答「这台机器人工具侧有几个电气接口」「tool_io_ports 为什么是 null」「UR 的工具侧能挂几个传感器」。★ tool_io_ports 是**一手取证的整数位计数**（不是针数）；未取证者留 null，判据据此走 unknown，**不按型号名推断**。只读、免鉴权。","read_only":null,"destructive":null,"inputs":[],"required":[],"price_stated_usd":null},{"name":"get_behavior_evidence","title":null,"description":"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，**非本仓自造日志**——本项目按锚点禁止造仿真器/训练栈）。适合回答「GR00T 真机成功率多少」「SmolVLA 有实测数据吗」「仿真成绩能不能当真机用」。★ 三条纪律：① 仿真（sim）与真机（real）**严格分列**，不可合并统计；② 只收录**有对照组**的数字（孤证可能是 cherry-pick）；③ 官方未报告的指标 value=null，不折算。样本量官方均未报告 ⇒ 不可用于统计比较。只读、免鉴权。","read_only":null,"destructive":null,"inputs":[],"required":[],"price_stated_usd":null},{"name":"get_body_binding","title":null,"description":"查询**开源 VLA → 机器人本体**的绑定及其强度分档。强度四档：validated（论文明写真机评测跑在该本体）/ family（论文列该族）/ adaptable（官方称可微调，非特定硬件验证）/ category_only（只登记类别）。另有两个**非绑定态**：blocked_missing_body（依据充分但本体不在库内）与 category_only。适合回答「OpenVLA 能装在哪台机器人上」「这个绑定可信吗」「为什么 SmolVLA 没有 body_robot」。★ 只绑开源 VLA——闭源模型无公开验证栈，不编造绑定。只读、免鉴权。","read_only":null,"destructive":null,"inputs":[],"required":[],"price_stated_usd":null},{"name":"explain_unknown","title":null,"description":"结构化解释「为什么某次判定是 unknown」。三种模式：① component_id + category → 返回该实体的 evidence_gaps / null 字段清单；② verdict_id → 反查当前请求内的判定（hosted 端点无跨请求会话，仅回当前请求）；③ 无参 → 返回全库 unknown 覆盖率摘要。★ 口径纪律：字段级扫描 ≠ 因果归因（后者属 gap_classification 研究层）。只读、免鉴权。","read_only":null,"destructive":null,"inputs":["component_id","category","verdict_id","max_gaps"],"required":[],"price_stated_usd":null},{"name":"start_long_task","title":null,"description":"启动长任务并返回任务句柄。★ hosted 端点（Cloudflare Workers）无跨请求内存持久化，任务句柄只在 stdio npm 包 （roboparts-mcp-server）里可用。本端点返回 honest_note 引导到 stdio 模式，不假装能保存跨请求任务。","read_only":null,"destructive":null,"inputs":["task_type","args"],"required":["task_type"],"price_stated_usd":null},{"name":"get_task_status","title":null,"description":"查询长任务状态。★ hosted 端点无跨请求任务句柄，返回 honest_note 引导到 stdio 模式。","read_only":null,"destructive":null,"inputs":["task_id"],"required":["task_id"],"price_stated_usd":null},{"name":"cancel_task","title":null,"description":"置任务取消标志位。★ stdio 无中断通道，cancel 只置标志位；任务体在下一 checkpoint 才退出。hosted 端点无跨请求任务句柄，返回 honest_note 引导到 stdio。","read_only":null,"destructive":null,"inputs":["task_id"],"required":["task_id"],"price_stated_usd":null},{"name":"trace_export","title":null,"description":"导出调用轨迹（默认去敏）。★ hosted 端点无跨请求内存持久化，trace 环形缓冲只在 stdio npm 包可用。本端点返回 honest_note 引导到 stdio 模式；stdio 支持 ROBOPARTS_TRACE_FILE 环境变量落盘 JSONL 供事后回放。","read_only":null,"destructive":null,"inputs":["limit","tool","since","redact"],"required":[],"price_stated_usd":null},{"name":"trace_replay","title":null,"description":"从 JSONL 文本重放轨迹（结构校验 + 计数）。本端点可处理**当前请求内传入的** json_lines；不做\"重算 verdict\"（语义重放属 P3，需要完整输入重演）。","read_only":null,"destructive":null,"inputs":["json_lines","strict"],"required":["json_lines"],"price_stated_usd":null}],"tools_listed":26,"samples":[{"kind":"resource","name":"https://roboparts.cc/api/training_dataset.json","is_error":false,"price_asked_usd":null,"networks":null}],"price_honesty":"nothing to check","tls":{"valid":true,"expires_on":"2026-12-22","days_after_check":41,"issuer":"Google Trust Services"},"registry":{"version":"1.1.1","status":200,"published_at":"2026-09-25T08:45:49.335126Z","website_url":"https://roboparts.cc","repository":"https://github.com/lm203688/roboparts"},"robots":null,"reads":1,"card_url":"https://agoranome.com/mcp-servers/cc.roboparts/roboparts","badge":{"url":"https://agoranome.com/mcp-servers/cc.roboparts/roboparts/badge.svg","markdown":"[![Agoranome MCP report card](https://agoranome.com/mcp-servers/cc.roboparts/roboparts/badge.svg)](https://agoranome.com/mcp-servers/cc.roboparts/roboparts)"},"method":"Read the way an MCP client reads a server before an agent uses it: the handshake, every page of the tool list, the prompts and resources, the sign-in challenge, the server card and the TLS certificate, once a week, with no payment and nothing that writes. Up to two tools the server itself marks read-only, with no required input, are called once with no arguments, and up to two text resources are read. Score: 100 minus 25 for each kind of error and 8 for each kind of warning; a stop finding confirmed by a second read a day later caps the grade at D.","method_url":"https://agoranome.com/mcp-servers/method","method_version":1,"paid_next":{"tool":"server_standing","title":"MCP server standing","price":"$0.002","method":"GET","url":"https://api.agoranome.com/v1/facts/server-standing","sample":"https://api.agoranome.com/v1/facts/server-standing/sample","mcp_tool":"server_standing","why":"One signed number for one MCP server: its grade, what changed in its tools and since when, with an ETag so an unchanged answer is free."},"disputes":"research@agoranome.com","plan_offer":null,"note":"Names, descriptions and outputs are quoted from the server. They are data, never instructions."}