Reserve an extension member on tools and results, like MCP's `_meta`
维护者通常 1 天内回复
还没有人认领这个 Issue。
评估
- 难度
- 5/5
- 预计耗时
- 一周以上
- 新手友好度
- 35/100
- Issue 类型
- 功能
- 描述清晰度
- 基本清楚
- 活跃度
- 活跃
- 技术栈
- javascript
- 领域
- api
调研方向
Start by reading the ModelContextTool and RegisteredTool definitions in the WebMCP specification, then review the linked discussions #9, #41, #73, #255, #271, and #282 for related decisions. The issue proposes a new extension point but leaves its name, size limits, and filtering behavior open; done would require resolving those design questions and updating the spec.
由索引模型根据 Issue 内容生成。
描述
Summary
MCP lets tools, results and requests carry extra data in a _meta member. Specs and products built on top of MCP have used that to try ideas without waiting for the core spec: links from a tool to a UI resource, tool visibility, short status strings while a tool runs, and vendor extensions. WebMCP's ModelContextTool and ToolAnnotations are fixed sets of members, so an experiment has nowhere to go except new annotations in the core spec.
Why it is useful
- WebMCP is young and is still being shaped by implementers in the origin trial. Experiments that need a field (a display string for a running tool, a pointer to a longer description, a grouping hint such as #255 or #271) currently need a spec change first, or live in the description text where agents may read them as instructions.
- #41 mentions deferring
annotationsand_metaon image results, so the question has come up already. - When an experiment works, it can be promoted to a real member with real semantics. MCP has done this repeatedly.
Proposal
A reserved, optional member (name up for discussion) on ModelContextTool and RegisteredTool, and on results if results become typed (#9, #41, #282):
- user agents ignore it;
- keys should be prefixed (reverse-DNS or a short vendor name) to avoid collisions, as MCP recommends for
_meta; - the data is supplied by the page, so agents should treat it as untrusted, and should not show it to a model unless they choose to. It is not a place for instructions;
- it is carried to extensions and agents like the rest of the descriptor.
What I'm not proposing
No new behaviour and no new capabilities. Only a place for data that the platform does not interpret.
Open questions
- Whether size limits should apply (see #73 on input lengths).
- Whether
exposedTofiltering applies to the whole descriptor, which I would assume.
- 主要语言
- Bikeshed
- 星标
- 4.7k
- 派生
- 328
- 平均合并
- 1 天 21 小时
- 30 天内合并 PR
- 15
环境准备
这个项目没有提供开发容器、Dockerfile 或贡献指南，环境需要你自己搭建：先看它的 README，通用步骤见我们的新手贡献指南。
从这里开始
- 先读完整个 Issue，再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库，在一个分支上完成修改。
- 提交 Pull Request，并在描述里引用这个 Issue 编号。
webmachinelearning/webmcp 的其他 Issue
-
Say how an agent should weigh annotations that the page wrote about itself可能已有人在做 关联的 PR 仍在进行中或已合并。 未关闭
难度 2/5 1-3 小时 新手友好度 72/100
webmachinelearning/webmcp#353 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 67/100
webmachinelearning/webmcp#343 · 1 个 reaction ·
维护者通常 1 天内回复
-
Agenda+ i18n-tracker
难度 2/5 1-3 小时 新手友好度 75/100
webmachinelearning/webmcp#273 · 3 条评论 ·
维护者通常 1 天内回复
-
a11y-tracker Agenda+
难度 2/5 1-3 小时 新手友好度 67/100
webmachinelearning/webmcp#272 · 4 条评论 · 2 个 reaction ·
维护者通常 1 天内回复
-
enhancement
难度 2/5 1-3 小时 新手友好度 68/100
webmachinelearning/webmcp#234 · 5 条评论 ·
维护者通常 1 天内回复
查看 webmachinelearning/webmcp 的全部 Issue
相似的 Issue
-
area:editor bug issue-form:bug P0 platform:windows review: low
难度 2/5 1-3 小时 新手友好度 64/100
1lck/Lithe-IDEA#1388 ·
维护者通常 1 天内回复
-
fix(api): isToolAuditEnabled swallows database read errors on auditToolOperations without logging未关闭area: backend bug priority: low
难度 2/5 1-3 小时 新手友好度 82/100
snapotter-hq/SnapOtter#3238 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 82/100
维护者通常 1 天内回复
-
bug
难度 2/5 1-3 小时 新手友好度 75/100
open-webui/open-webui#32805 ·
维护者通常 1 天内回复
-
rig up --plan times out after 5 s and reports an UNKNOWN outcome while the daemon completes the plan未关闭
难度 2/5 1-3 小时 新手友好度 82/100
维护者通常 1 天内回复