LesenForschungRadarAnlageframework
Anmelden / Registrieren
← Zurück zur Lektüre
NewsThema · MCP协议不对称争议Wesentlich3 Min. LesezeitDisconfirmAI Redaktion

AWS Developer Advocate James Ward: MCP Servers Should Be the Third Voice in Conversations, Driving Tool Iteration with Guidance and Session Tracing

James Ward of AWS believes that when MCP servers return data, they should carry next-step guidance and stitch together complete call paths via session IDs, enabling teams to observe agent behavior, identify tool defects, and validate improvements through evaluations.

2026-10-29 23:55 GMT+8

At the AGNTCon + MCPCon conference, James Ward, a senior developer advocate at AWS, put forward a core argument regarding MCP server design: the protocol's best use is not for servers to act as databases, but to serve as a third voice in the conversation. He envisions a scenario where, when you have multiple MCP servers, they each play the role of a fourth or fifth participant in the dialogue, rather than merely being queried data sources.

The specific mechanism Ward proposes is this: tool responses should not only return data but also carry guidance—telling the agent what it just did, what it might want to do next, and where to find more information. This means MCP servers transform from passive query interfaces into active participants; their output itself becomes the input for the agent's next step in reasoning.

Observability is the other half of this proposition. Ward points out that while web developers can trace a single page click all the way down to the database, MCP has no default trace ID mechanism. AWS's solution is quite straightforward: add a session ID parameter to tools and require agents to pass it with every call, thereby stitching scattered calls into a complete path. A second parameter can carry the user's original prompt or a summary of their goal. Teams can then compare what the user wanted with the path the agent actually took, build evaluations around this path, adjust tool descriptions or parameters, and measure whether task completion rates improve.

A concrete example illustrates the value of this approach. In a profile piece published by the Agentic AI Foundation, Ward described a scenario where an agent fetched customer records one by one because the server only provided a single-record query tool. It was by observing the complete call path that the team spotted this pattern and subsequently built a batch tool to fix it. Without end-to-end visibility, such inefficient calls could remain hidden beneath the surface of seemingly normal operations for a long time.

Anmelden / Registrieren
LesenForschungRadarAnlageframework

Ward does not present MCP as the sole solution. He acknowledges that AWS also offers CLIs and skills interfaces, partly because MCP's OAuth model cannot switch between AWS user profiles the way a CLI can. Which method works best depends on the model, tool descriptions, and how the agent discovers tools, so AWS compares them side-by-side using evaluations. He also admits that this methodology is not novel—observing paths, reproducing issues, measuring improvements, and iterating on tools are old principles of software engineering; the new requirement is simply to understand the path taken jointly by humans and agents, and to verify whether changes to tools truly help complete tasks.

Notably, this article was sponsored by AWS Marketplace, and Ward himself is an AWS employee; the practices described are those used by internal AWS developers for their MCP servers. This is an engineering proposition from a vendor perspective, not the result of independent third-party verification. The session ID scheme relies on agents cooperating to pass parameters; it is not a mandatory constraint at the protocol level. Whether it can be promoted across the broader MCP ecosystem depends on whether various implementations are willing to accept this convention.

Quellen

  • thenewstack.ioThe New Stack↗
Thema

MCP协议不对称争议

【背景】Model Context Protocol (MCP) 由美国人工智能实验室 Anthropic 创建,旨在标准化 AI 代理与外部工具的连接。近期,围绕该协议的争议焦点从单纯的技术兼容性转向了生态权力的结构性不对称。

3 Schritte2 BeiträgeAktualisiert 2026-11-06 07:15

Wie es dazu kam

  1. 2026-10-20Figma 联合创始人 Dylan Field 在 Config India 会议上回应外界批评时,公开质疑 MCP 协议存在结构性不对称,指出 Anthropic 未通过 MCP 暴露自身云端资源。techcrunch.com ↗
  2. 2026-10-21Figma 正式宣布新增20个 MCP 合作伙伴,包括 Notion、Mistral 等,同时 Field 重申对协议改进空间的看法,并提及出于滥用风险考虑不会完全开放所有数据。startupfortune.com ↗
  3. 2026-10-31AWS 开发者倡导者 James Ward 在 AGNTCon + MCPCon 会议上提出,MCP 服务器应携带指引和会话 ID,以解决默认缺乏追踪 ID 的问题,提升代理行为的可观测性。thenewstack.io ↗

Was noch ungeklärt ist

  • Anthropic 是否会调整策略,通过 MCP 暴露更多自身生成的工件或云端资源以缓解不对称争议?
  • 针对 MCP 规范中可选条款导致的 SDK 安全漏洞,Linux Foundation 下的 Agentic AI Foundation 是否有具体的修复时间表?
  • 其他大型应用平台(如 Canva 或 Microsoft)是否会在接入 MCP 时采取类似 Figma 的‘选择性开放’策略以保护数据主权?

Auch in diesem Thread

  • Figma Co-founder Dylan Field Says MCP Favors Frontier Labs2026-10-21
Vollständiges Thema lesen →
Recherche fortsetzen →