docs(mcp): default the example to OpenAI + Zilliz Cloud (match claude-context)#147
Merged
zc277584121 merged 1 commit intoJun 30, 2026
Conversation
…liz Cloud Mirror claude-context's setup in the MCP example: recommend configuring the MFS server with OpenAI text-embedding-3-small embeddings and a Zilliz Cloud vector store (OPENAI_API_KEY + ZILLIZ_URI/ZILLIZ_TOKEN, embedding model in server.toml), with the fully-local ONNX + Milvus Lite path noted as the alternative. The embedding and vector-store choice lives on the MFS server, so the MCP server (a thin client) still only needs MFS_URL/MFS_TOKEN. Signed-off-by: Cheney Zhang <chen.zhang@zilliz.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Scope: the MCP example only — MFS's own product defaults are unchanged (still local ONNX + Milvus Lite).
To replicate claude-context as closely as possible, the MCP example now recommends configuring the MFS server with the same model and store it ships with — OpenAI
text-embedding-3-smallembeddings and a Zilliz Cloud vector database (OPENAI_API_KEY+ZILLIZ_URI/ZILLIZ_TOKEN, with the embedding model inserver.toml). The fully-local ONNX + Milvus Lite path is kept as the noted alternative.Because MFS does the embedding and storage, that config lives on the MFS server; the MCP server is a thin client and still only needs
MFS_URL/MFS_TOKEN. No code change — docs only.mkdocs build --strictpasses.