docs(ai): 补充远程 MCP Inspector 调用示例 - #2913
Merged
Snailclimb merged 1 commit intoSep 5, 2026
Merged
Conversation
georgeatparallel
marked this pull request as ready for review
September 4, 2026 23:55
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
补充一个可运行的远程 MCP 示例,放在现有的本地天气 Server 和 Inspector 调试示例之后。读者可以用同一个 Inspector CLI,通过 Streamable HTTP 列出工具,再搜索 Java 虚拟线程的官方资料。
选 Parallel 还有一个可以直接核对的理由:Artificial Analysis 的 Search API 评测中,Parallel fast 在 DeepSearchQA 上拿到 80 分,比 Brave web 高 18 分、You.com snippets 高 17 分、TinyFish web 高 13 分。对需要多次搜索、整理资料的任务,这个结果让我觉得它值得放进教程,给读者一个可以亲手试的选择。
下面列出该榜单全部 9 家服务商、19 种模式的 DeepSearchQA F1,方便对照。数据更新日期为 2026-08-31,分数按页面显示的 0–100 刻度记录;在榜单的 provider 筛选器中选 Select all 可以看到所有条目。
另一个差距比较明显的项目是 BrowseComp:Parallel fast 是 72,Tavily basic 是 59,相差 13 分。这个指标考察的是需要多步检索才能找到的事实。
速度也适合拿来做交互式示例:Parallel fast 的平均每任务时间是 19.4 秒,在全部 19 种模式中最低。这里是榜单定义的任务时间,包含推算的模型时间和实测搜索时间,不是一次搜索请求的延迟。时间数据 · 评测方法
这些优势对应具体指标。综合三项评测的 Search Index,Perplexity medium 是 80,Parallel fast 是 73,不能据此说 Parallel 在所有任务上都最好。本教程的匿名 MCP 默认使用 fast 模式;上面的分数来自 Artificial Analysis 的 Search API 测试,不是对这个 MCP 示例的直接评测。
示例使用 Parallel Search MCP 的匿名入口,不需要账号或 API Key。文中说明了速率限制、请求数据会发送给 Parallel,以及 HTTP 200 和工具执行成功的区别。这次只修改教程,不添加依赖或客户端配置。
验证:
web_search、web_fetch,搜索成功返回 OpenJDK JEP 444 的链接和摘录。git diff --check。我在 Parallel 工作,这项服务由 Parallel 运营。