diff --git a/en/learn-more/extended-reading/dify-docs-mcp.mdx b/en/learn-more/extended-reading/dify-docs-mcp.mdx
index 768004f0..532cd12c 100644
--- a/en/learn-more/extended-reading/dify-docs-mcp.mdx
+++ b/en/learn-more/extended-reading/dify-docs-mcp.mdx
@@ -104,3 +104,26 @@ The MCP approach lets you describe problems in natural language. Even when you'r
| Principle | Splits documents into text chunks and builds indexes using vector embeddings. When users ask questions, the system calculates similarity between questions and text chunks, then selects relevant chunks as context for generating answers. | AI actively generates query strategies based on question requirements. Supports multi-round interactive queries and adjusts subsequent searches based on initial results. |
| Advantages | Fast processing speed, suitable for large-scale static documents. | - Can access complete document content, supports cross-chapter complex queries
- No complex reprocessing after document updates—simply regenerate MCP service
- Provides coherent and complete answers |
| Limitations | - Static document splitting may fragment related information
- Vector similarity-based retrieval may miss semantically related but lexically different content
- Context window limitations—only generates answers based on specific chnks | - Requires significant token consumption, higher cost
- Relies on LLM's query strategy generation capability, may affect retrieval accuracy
- Multi-round interactive queries may lead to longer response times
- Requires additional MCP server deployment and maintenance costs |
+
+{/*
+Contributing Section
+DO NOT edit this section!
+It will be automatically generated by the script.
+*/}
+
+
+
+ Help improve our documentation by contributing directly
+
+
+ Found an error or have suggestions? Let us know
+
+
diff --git a/zh-hans/learn-more/extended-reading/dify-docs-mcp.mdx b/zh-hans/learn-more/extended-reading/dify-docs-mcp.mdx
index 69b0ed5a..f5723ff6 100644
--- a/zh-hans/learn-more/extended-reading/dify-docs-mcp.mdx
+++ b/zh-hans/learn-more/extended-reading/dify-docs-mcp.mdx
@@ -104,3 +104,26 @@ MCP 方式允许用自然语言描述问题,即使不确定具体技术术语
| 工作原理 | 预先将文档分割成文本块,使用向量嵌入建立索引。用户提问时,系统计算问题与文本块相似度,选择相关块作为上下文生成答案。 | AI 根据问题需求主动生成查询策略,支持多轮交互查询,根据初次结果调整后续搜索。 |
| 优势 | 处理速度快,适合大规模静态文档集合。 | - 可访问完整文档内容,支持跨章节复杂查询
- 文档更新后无需再次进行繁琐处理,重新生成 MCP 服务即可提供查询服务
- 提供连贯完整的答案 |
| 局限性 | - 静态文档分割可能分散相关信息
- 基于向量相似度检索可能遗漏语义相关但词汇不同的内容
- 上下文窗口限制,仅基于特定片段生成答案 | - 需要消耗大量 Tokens,成本较高
- 依赖 LLM 的查询策略生成能力,可能影响检索准确性
- 多轮交互查询可能导致响应时间较长
- 需要额外的 MCP 服务器部署和维护成本 |
+
+{/*
+Contributing Section
+DO NOT edit this section!
+It will be automatically generated by the script.
+*/}
+
+
+
+ 通过直接提交修改来帮助改进文档内容
+
+
+ 发现错误或有改进建议?请提交问题反馈
+
+