roboparts
Registry code: 8794e7f7cf690271
RoboParts 是仿生/人形机器人零部件的兼容性数据层(执行器、传感器、芯片、通信协议、接口、平台、具身智能模型等 20 个品类)。
适合用它来做:确认两个零件能否搭配、按场景筛选候选件、核对某个参数的口径是否可比。
- endpoint
- https://roboparts.cc/mcp
- door code
- e991ef8567ff1265
- protocol
- streamable-http ·2025-06-18
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is roboparts live?
- Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
- Is roboparts free to use?
- Yes — the hub reached it with no key and no payment.
- What tools does roboparts have?
- 26 tools: start_long_task, compare_components, review_compatibility, lint_urdf, explain_compose_frontier, explain_evidence_cohort, explain_evidence_mdv, explain_connector_types, ….
- Is roboparts safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 99.3%· all time 99.5%
last good check
of 26 tools
- degraded → live
- live → degraded· timeout after 20000ms
- degraded → live
- live → degraded· timeout after 20000ms
- down → live
- topic
- iot & hardware robotics
- used for
- check compatibility of two robot parts
- search robot components
- compare component specs
- lint a urdf file
- recommend parts for an application
- takes → gives
- text, code → data
- tools
- 11 reads
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
get_research_progress open 18h ago
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」。
{ "type": "object", "required": [], "properties": {} }arguments 5 linesget_robot_tool_side open 18h ago
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。
{ "type": "object", "required": [], "properties": {} }arguments 5 linescheck_co_mount open 1h ago
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。
{ "type": "object", "required": [], "properties": { "a": { "type": "string", "description": "器件 A 的实体 id,如 ACT-028。需与 b 同时给。" }, "b": { "type": "string", "description": "器件 B 的实体 id,如 SENS-047。需与 a 同时给。" }, "host": { "type": "string", "description": "宿主机器人 id,如 HUB-030(UR3e)、HUB-031(UR5e)、SUPERDEX-fr3。" } } }arguments 18 linesget_behavior_evidence open 1h ago
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。
{ "type": "object", "required": [], "properties": {} }arguments 5 linesget_body_binding open 1h ago
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。
{ "type": "object", "required": [], "properties": {} }arguments 5 linesget_parameter_semantics reads open 6h ago
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。
{ "type": "object", "properties": {} }arguments 4 linesget_standard_audit reads open 6h ago
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。
{ "type": "object", "properties": { "scope": { "enum": [ "all", "conflicts" ], "type": "string", "default": "all", "description": "返回范围:all=完整审计报告(默认);conflicts=仅数据质量冲突条目。" } } }arguments 14 linessearch_components reads open 6h ago
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。
{ "type": "object", "properties": { "limit": { "type": "number", "default": 10, "description": "返回条数上限,默认 10,最大 50(超出按 50 截断)。" }, "keyword": { "type": "string", "description": "关键词,对 name / name_en / manufacturer / type / protocol / interface / description 七个字段做大小写不敏感的**子串**匹配(非分词、非模糊、不纠错)。**中英文命中集合可能完全不重叠**,务必两种都试:实测 \"六维力\" 命中 16 条、\"force torque\" 命中 2 条、交集为 0(部分国产条目尚无英文名)。多个词不做 AND 拆分,\"harmonic drive 20Nm\" 会被当作一整个串匹配,实测返回 0 条;请只给一个词(如 \"harmonic\" 命中 9 条),再用 category 收窄。" }, "category": { "enum": [ "actuators", "sensors", "chips", "interfaces", "protocols", "llms", "platforms", "flexible_actuators", "robot_ai_models", "data_acquisition", "connectors", "integrated_joints", "reducers", "controllers", "grippers", "structural", "cables", "power", "pcb", "bionic_mechanisms" ], "type": "string", "description": "品类精确筛选,取值必须来自 enum(严格相等,不做别名映射:传 \"actuator\"、\"电机\" 均返回空)。不传则跨全部 20 个品类检索。注意品类与 ID 前缀不是一一对应的,请以本字段为准。" }, "include_market_intelligence": { "type": "boolean", "default": false, "description": "默认 false。库内另有 3 条市场情报条目(专利地图/咨询报告/趋势条目),它们不是可采购零件,默认不返回;仅在你确实想查行业研究材料时设为 true。" } } }arguments 45 linesstart_long_task unknown never probed
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。
{ "type": "object", "required": [ "task_type" ], "properties": { "args": { "type": "object", "description": "任务参数" }, "task_type": { "enum": [ "batch_check_compatibility", "bulk_export_bom", "deep_dialect_evaluate" ], "type": "string", "description": "预定义任务类型" } } }arguments 21 linescompare_components reads unknown never probed
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。
{ "type": "object", "required": [ "ids" ], "properties": { "ids": { "type": "array", "items": { "type": "string" }, "maxItems": 6, "minItems": 2, "description": "待对比零部件 ID 数组(2~6 个),形如 [\"ACT-001\", \"ACT-002\"]。请先用 search_components 确认 ID。" } } }arguments 17 linesreview_compatibility reads unknown never probed
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。
{ "type": "object", "required": [ "component1_id", "component2_id" ], "properties": { "component1_id": { "type": "string", "description": "零件 1 的 ID,形如 ACT-001 / CHIP-001 / PROTO-012。请先用 search_components 取得,不要自行拼造。" }, "component2_id": { "type": "string", "description": "零件 2 的 ID,取值方式同 component1_id。两个 ID 可以属于不同品类。" } } }arguments 17 lineslint_urdf reads unknown never probed
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。
{ "type": "object", "required": [ "urdf_xml" ], "properties": { "urdf_xml": { "type": "string", "description": "URDF XML 文件内容(完整 XML 字符串,含 <?xml ... ?> 声明)。支持 DOMParser 与正则 fallback 双解析路径。最大 512KB,超出截断并返回 parse_error。" }, "check_level": { "enum": [ "all", "errors_only", "warnings_and_errors" ], "type": "string", "default": "all", "description": "检查严格度:all=全部检查(默认),errors_only=仅返回 error 级别,warnings_and_errors=warning+error。" } } }arguments 22 linesexplain_compose_frontier unknown never probed
【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。
{ "type": "object", "required": [], "properties": { "component1_id": { "type": "string", "description": "零件 1 的 ID,形如 ACT-001 / GRIP-002 / SENS-852。请先用 search_components 取得。" }, "component2_id": { "type": "string", "description": "零件 2 的 ID。若省略,则只返回库级聚合结论(frontier 概览 + composed 归因)。" } } }arguments 14 linesexplain_evidence_cohort unknown never probed
【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。
{ "type": "object", "required": [], "properties": {} }arguments 5 linesexplain_evidence_mdv unknown never probed
【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。
{ "type": "object", "required": [], "properties": {} }arguments 5 linesexplain_connector_types unknown never probed
【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。
{ "type": "object", "required": [], "properties": {} }arguments 5 linesexplain_unknown unknown never probed
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。
{ "type": "object", "properties": { "category": { "enum": [ "actuators", "sensors", "chips", "interfaces", "protocols", "llms", "platforms", "flexible_actuators", "robot_ai_models", "data_acquisition", "connectors", "integrated_joints", "reducers", "controllers", "grippers", "structural", "cables", "power", "pcb", "bionic_mechanisms" ], "type": "string", "description": "品类:actuators / sensors / chips / interfaces / protocols / llms / platforms / flexible_actuators / robot_ai_models / data_acquisition / connectors / integrated_joints / reducers / controllers / grippers / structural / cables / power / pcb / bionic_mechanisms" }, "max_gaps": { "type": "number", "default": 20, "description": "最多返回多少条缺口" }, "verdict_id": { "type": "string", "description": "判定 verdict_id(hosted 端点仅当前请求内可查)" }, "component_id": { "type": "string", "description": "组件 ID,如 ACT-001、SENS-001" } } }arguments 44 linesget_task_status unknown 21h ago
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。
{ "type": "object", "required": [ "task_id" ], "properties": { "task_id": { "type": "string", "description": "任务 ID(stdio 模式下 start_long_task 返回)" } } }arguments 12 linescancel_task unknown never probed
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。
{ "type": "object", "required": [ "task_id" ], "properties": { "task_id": { "type": "string", "description": "任务 ID" } } }arguments 12 linestrace_export unknown never probed
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。
{ "type": "object", "properties": { "tool": { "type": "string", "description": "按工具名过滤" }, "limit": { "type": "number", "default": 200, "description": "最多返回多少条" }, "since": { "type": "string", "description": "ISO 8601 时间戳起点" }, "redact": { "type": "boolean", "default": true, "description": "是否去敏(默认 true)" } } }arguments 23 linesbom_compatibility_check reads unknown 18h ago
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。
{ "type": "object", "required": [ "component_ids" ], "properties": { "component_ids": { "type": "array", "items": { "type": "string" }, "description": "待校验的零件 ID 列表,如 [\"ACT-001\",\"SENS-001\",\"PROTO-012\"]。ID 必须真实存在:先用 search_components 取得,不要自行拼造(ID 前缀与 category 非一一对应)。支持主库零件与开源贡献层 OSS-xxx 混合。至少传 2 个才有意义。" } } }arguments 15 linessemantic_search reads unknown 12h ago
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。
{ "type": "object", "required": [ "query" ], "properties": { "k": { "type": "number", "default": 5, "description": "语义召回返回的候选零部件条数(top-k),默认 5,取值 1–30;数值越大召回越广但越可能偏离查询意图。" }, "query": { "type": "string", "description": "自然语言查询,如\"六维力传感器 防水\"或\"ROS2 通信模组\"。中英文均可,建议具体。" } } }arguments 17 linestrace_replay unknown never probed
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)。
{ "type": "object", "required": [ "json_lines" ], "properties": { "strict": { "type": "boolean", "default": false, "description": "严格模式:首个 parse 失败即中断" }, "json_lines": { "type": "array", "items": { "type": "string" }, "description": "JSONL 行数组(每行一条 trace JSON)" } } }arguments 20 linesrecommend_for_application reads unknown never probed
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。
{ "type": "object", "required": [ "application" ], "properties": { "count": { "type": "number", "default": 3, "description": "每品类返回条数,默认 3,上限 10(超出按 10 截断)。四个品类各自独立计数。" }, "budget": { "type": "number", "description": "单件预算上限(USD,正数),可选。**价格字段覆盖率有限**(实时覆盖数见 GET /mcp 的 dataset.priced),因此本参数只能剔除「确定超预算」的条目,不能保证结果全部在预算内。每条结果会附 price_fit:within(确定在预算内)/ partial(区间跨越预算)/ unknown(库内无价格,未经校验)。不传则不做任何价格筛选,也不返回 price_fit。" }, "application": { "enum": [ "humanoid", "quadruped", "robot_arm", "amr", "industrial" ], "type": "string", "description": "应用场景,必填,取值限 enum。判定方式是拿一组固定场景词去匹配条目的 applications/name/type/description 字段,而非人工标注的场景分类:humanoid=人形/双足,quadruped=四足,robot_arm=机械臂/协作臂,amr=移动机器人/AGV,industrial=工业产线。若某品类下无任何条目命中该场景,该品类会退化为品类罗列并在 scene_matched=false 中标明,此时结果不代表适配该场景,应改用 search_components 按具体参数筛选。" } } }arguments 28 linescheck_compatibility reads unknown 12h ago
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。
{ "type": "object", "required": [ "component1_id", "component2_id" ], "properties": { "component1_id": { "type": "string", "description": "零件 1 的 ID,形如 ACT-001 / CHIP-001 / PROTO-012。请先用 search_components 取得,不要自行拼造:ID 前缀与 category 并非一一对应(例如 sensors 品类下存在 CHIP-67,platforms 下存在 ACT-patsnap-actuator;实时不一致条数见 GET /mcp 的 dataset.id_category_mismatch),按品类猜前缀会取到错误条目或直接查无此项。" }, "component2_id": { "type": "string", "description": "零件 2 的 ID,取值方式同 component1_id。两个 ID 可以属于不同品类(跨品类比对正是本工具的用途)。" } } }arguments 17 linesget_component_detail reads unknown 12h ago
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。
{ "type": "object", "required": [ "id" ], "properties": { "id": { "type": "string", "description": "零部件 ID,如 ACT-001 / CHIP-001 / SENS-001。大小写与连字符需完全匹配,不做模糊查找;建议先由 search_components 返回值取得。注意 ID 前缀不能反推 category(库内存在前缀与品类不一致的条目,实时条数见 GET /mcp 的 dataset.id_category_mismatch)。" } } }arguments 12 lines
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's id8794e7f7cf690271.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/8794e7f7cf690271/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/8794e7f7cf690271?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.