Skip to content
Agentmart
Submit a tool

Local FAISS MCP Server

Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.

Connector by nonatofabio · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 36
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/nonatofabio-local-faiss-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
2 read · 1 write · 0 delete · 1 not yet classified
Secrets
None asked for
Install scripts
Not scanned yet
Runs as
Python package

Tools by what they do 4

Read from the source code; the running server may list different tools.

Read 2 · Look things up without changing anything.

  • query_rag_store
  • recall

Write 1 · Create, change, send or run things.

  • remember

Not yet classified 1 · We could not tell from the name and description.

  • ingest_document

Files it touches

  • Any path the agent passes to its tools

Tools (4)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • ingest_document

    Ingest a document into the FAISS vector store. The document will be chunked, embedded, and stored for later retrieval.

  • query_rag_store

    Query the FAISS vector store to retrieve relevant document chunks based on semantic similarity.

  • recall

    Search long-term memory for relevant past context. Use this BEFORE starting a new task to check for: previous attempts, known solutions, user preferences, architectural decisions, and past errors. This avoids repeating mistakes and ensures consistency with prior work. Query with natural language — the search is semantic, not keyword-based.

  • remember

    Store important information in long-term memory. By default, checks for similar existing memories first. If similar memories are found, review them and call remember again with update_id to replace an existing memory, or force=true to store as new.

Signals

Stars
36
Forks
13
Open issues
2
Contributors
4
Weekly downloads
48
Last commit
Apr 24, 2026 (6 months ago)
Last release
Feb 9, 2026 (8 months ago)
Last package publish
Feb 9, 2026 (8 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.nonatofabio/local-faiss-mcp
Version
0.2.0-rc.3
Auth
No auth
Packages
pypi local-faiss-mcp
License
MIT
Repository
github.com/nonatofabio/local_faiss_mcp
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

Local FAISS MCP Server. Agent Mart. https://agentmart.dev/connectors/nonatofabio-local-faiss-mcp (last updated 2026-10-24)