MCP servers · ayush-yadav11

quillrag: single-binary local RAG MCP server in Rust

A local retrieval-augmented search server in Rust, shipped as one binary, that indexes local files and exposes hybrid search over MCP.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

quillrag is a local RAG engine distributed as a single static binary. It embeds the all-MiniLM-L6-v2 model and combines dense cosine search with BM25 keyword retrieval using Reciprocal Rank Fusion. It exposes four MCP tools, rag_index, rag_search, rag_status and rag_clear, and offers CLI equivalents that use the same engine.

It suits MCP clients such as Claude Desktop or Cursor when the assistant should search a local directory of notes or documents during a conversation. Indexing is incremental: unchanged files are skipped, only changed files are re-embedded, and pruning is limited to the directory passed in. Symlinked files and directories are followed. Default indexed types cover Markdown, plain text, common data and config formats, and many source languages; dot-directories, node_modules and similar build folders are ignored. The publisher reports about 20 ms to a ready server and about 25 ms per query on a 2-core CPU with a small corpus.

The quickest route is a prebuilt archive from the latest release, available for Windows x86_64, macOS Apple Silicon and Linux x86_64, or a build from source with cargo. Index data is stored in a single redb file. Embeddings, storage and search run locally, and the server makes no network calls after installation. When used as a library, optional PDF and OCR extractors can be enabled.

Limitations and requirements

Binaries for v0.1.6 are built against glibc 2.39, so older Linux distributions need a source build. OCR works for English and basic Latin text only. Indexes built by older batched indexing may associate paths with the wrong chunks; the fix requires building a fresh data directory from the source files.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    quillrag

    Single-binary local RAG MCP server in Rust. MiniLM compiled in, hybrid search, zero deps.

    v0.1.3
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
modelcontextprotocol

MCP reference servers

Seven small example servers maintained by the Model Context Protocol project: files, Git, web fetching, memory, time, step-by-step thinking and a test server.

92K GitHub starsSoftware development
Updated 18 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
firecrawl

Firecrawl MCP Server (web search and scraping)

Firecrawl's MCP server that lets an AI assistant search the web, turn pages and PDFs into clean Markdown, crawl sites and interact with dynamic pages.

7.8K GitHub starsWeb, search & browserProductivity & automation
Updated 17 Nov 2026
quillrag: single-binary local RAG MCP server in Rust | AI Gate Discover