RoboParty MCP
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LAYA_CACHE | No | Cache directory for the Laya model used by System-1. | |
| MCP_CONFIG | No | Configuration file path for the control MCP subprocess. | |
| LAYA_MIRROR | No | Mirror used when fetching the Laya model. | |
| RP_TLS_CERT | No | Path to the robot certificate used by the control subprocess. | |
| LAYA_REVISION | No | Laya model revision to fetch. | |
| LAYA_SUBFOLDER | No | Subfolder for the Laya model in the cache. | |
| RP_SERVICE_TOKEN | No | rp_server Bearer token used by the control subprocess. | |
| RP_ALLOW_PLAINTEXT | No | Allow ws:// for local debugging only in the control subprocess. | |
| ONNXRUNTIME_NODE_INSTALL | No | Set to skip to skip onnxruntime-node download during install, e.g. when using roboparty-mcp --fetch-model afterward. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| docs_list_manualsA | [docs] 列出可用资料：RoboParty 公开文档的产品、分类与页数，以及已索引的 RP1 GitHub 仓库/页数。回答机器人问题前先用它了解可用资料。 |
| docs_search_docsA | [docs] 在 RoboParty 公开文档中检索：roboparty.com 文档全文 + RP1 各 GitHub 仓库的 README/docs（kind=github；私有仓库需 gh auth login）。传短查询：错误原文、命令、接口名、仓库名或几个关键词，不要贴整段话。默认按查询语言自动选择中文/英文并优先该语言。命中后用 get_page 打开 url，用原文回答并附链接。不要凭记忆编造管脚、包名、版本或步骤。 |
| docs_get_pageA | [docs] 读取一篇资料为 Markdown：roboparty.com 文档页面或 RP1 GitHub 仓库的 README/docs。传入 search_docs 命中的 url；可传 section（标题/锚点）只取相关小节，full=true 取整页，maxChars 控制长度。每个问题最多打开 1–2 篇。 |
| docs_list_tocC | [docs] 列出某一分类下的文档，或已索引的 RP1 GitHub 仓库（manual 传分类名，或 rp1/github/repo）。 |
| system1_laya_analyzeA | [system1] Run Laya once over a state and typed questions. Returns calibrated choice/score/noul answers with probabilities. Analysis only; it does not control the robot. |
| system1_laya_healthA | [system1] Return whether the Laya model is loaded, loading, or failed, plus last latency. |
| system1_laya_infoA | [system1] Return Laya model path, source, execution providers and loaded config. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
The four docs tools form a clear retrieve-narrow-read chain (list_manuals -> list_toc -> search_docs -> get_page), though list_manuals and list_toc both enumerate material at different granularity and could occasionally be swapped. The three system1_laya tools are cleanly split between inference (analyze), status (health), and configuration (info), so boundaries are clear overall.
Both namespaces use a predictable prefix plus action pattern: docs_<verb>_<noun> and system1_laya_<action>. Minor deviation only in that health and info are noun-like states rather than verbs like analyze, but everything stays snake_case and readable.
Seven tools is well within the sweet spot, and each one covers a distinct step: enumerate sources, browse a category, search full text, open a page, plus three model-introspection calls. No filler or duplicate tools are present.
The docs surface covers the full discovery-to-read lifecycle (list manuals, list TOC, search, fetch page with section/limit options), and the Laya surface covers inference plus health and configuration introspection. The only 'gap' is robot control, which is explicitly out of scope for this analysis-only server, so no dead ends remain.