[Feature] Add support for MCP in DeepSeek R1 0528

[somax]

MaxKB Version

v1.10.8-lts

Please describe your needs or suggestions for improvements

已知 DeepSeek R1 0528 版是支持 Function Calling 和 MCP ，但是在 MaxKB 中实际测试，在该AI 对话节点不会有任何输出。通过关闭 MCP 工具和更换 Qwen3 模型重复验证了只有在 R1 0528 和 MCP 开启才会出现的问题。

Please describe the solution you suggest

根据 B 站九天的公开课视频得知，R1 0528 返回数据和常见的如 Qwen3 等大模型不同，需要额外处理首次对话的返回数据结构。
相关视频供参考：https://www.bilibili.com/video/BV1h77jzoEak/?p=4&t=577

Additional Information

No response

[somax]

网络问题重复提交

[shaohuzhang1]

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

---

Repeated submission of network issues

[liqiang-fit2cloud]

MCP工具的调用效果取决于LLM的质量和MCP服务的质量，建议你尝试更换大模型、计算平台或者MCP。
MaxKB本身没有也不会对某个大模型或某个计算平台做特殊处理，个别模型返回数据的差异会由ollma、vllm等内部处理，它们暴露接口的返回数据不会有变化。

[shaohuzhang1]

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

---

The calling effect of MCP tools depends on the quality of LLM and the quality of MCP services. It is recommended that you try to replace the large model, computing platform or MCP.
MaxKB itself does not and will not do special processing for a large model or a computing platform. The differences in data returned by individual models will be processed internally by ollma, vllm, etc., and the data returned by their exposed interfaces will not change.