
Local FAISS MCP Server
- 33 repo stars
- Updated April 24, 2026
- nonatofabio/local_faiss_mcp
Runs a local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts, letting an agent index and query your own documents on your machine without a cloud service.
About
Local FAISS MCP Server runs a FAISS vector database on your own machine for retrieval-augmented generation, with document ingestion, semantic search, and bundled MCP prompts. A solo builder reaches for it to index private documents and let an agent query them without sending data to a cloud vector service. It installs from pypi over stdio and keeps everything local.
- Local FAISS vector database for RAG
- Document ingestion and semantic search
- Bundled MCP prompts
- Runs fully local, pypi package
Local FAISS MCP Server by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add local-faiss-mcp -- uvx local-faiss-mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| repo stars | ★ 33 |
|---|---|
| Package | local-faiss-mcp |
| Transport | STDIO |
| Auth | None |
| Last updated | April 24, 2026 |
| Repository | nonatofabio/local_faiss_mcp ↗ |
What it does
Runs a local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts, letting an agent index and query your own documents on your machine without a cloud service.
Who is it for?
Builders wanting private, local RAG over their own documents
Skip if: Teams needing a managed cloud vector service