LabscoMCP early access ↗
ChrisGVEMCP SERVER

Workspace-Qdrant-MCP

A project-scoped vector database for coding assistants: hybrid semantic and keyword search over your codebase, plus a place to store findings so the next session can retrieve them.

by ChrisGVE ↗Code Intelligence & Repository IndexingCommunity

LABSCO SUMMARY

Storing is half the point, not an afterthought.

Most code-search servers only read. Here the write path is the design: findings, design rationale and research go into a scratchpad that later sessions — and sub-agents, which start with no history at all — can search semantically. The README ships the CLAUDE.md text to make an assistant use it that way, including the three-step habit of searching first, falling back to plain file tools second, and storing what was learned at the end. Note the rebuild in progress before you commit a large index to it.

What it is

A Qdrant-backed search layer with automatic Git project detection, a Rust daemon doing the file watching and embedding, and a Rust CLI for operations. Search combines semantic similarity with keyword matching using Reciprocal Rank Fusion; code is chunked with Tree-sitter and enriched with LSP data for active projects.

What you get

  • Hybrid semantic and keyword search across indexed content, plus exact substring and regex search over FTS5 — search, grep
  • Direct document lookup by id or metadata filter, and file and folder listing for exploring project structure — retrieve, list
  • A write path: store content, register projects, and save notes so findings survive the session — store
  • Persistent behavioural rules that load back into context at the start of a session — rules
  • Four collections with different scopes: indexed project code, a library of external reference docs, a scratchpad for analysis and design rationale, and the rules themselves
  • A code relationship graph with PageRank, community detection and betweenness centrality, queried from the CLI
  • A background daemon that watches files continuously, so the index tracks the working tree without manual re-ingestion

Requirements

  • A running Qdrant reachable at QDRANT_URL — the README's one-liner starts the qdrant/qdrant image on port 6333 with a storage volume.
  • The server has to be built from source: clone the repository and run ./install.sh, which compiles it and copies wqm, memexd and workspace-qdrant-mcp into ~/.local/bin, so that folder needs to be on your PATH. The README's Homebrew and download-script options do not currently deliver the server itself.
  • The build needs the Rust toolchain (cargo).
  • A C compiler, because Tree-sitter grammars ship as C source and are compiled locally — Xcode Command Line Tools on macOS, build-essential on Debian or Ubuntu.
  • Clang and LLVM for the daemon, unless you build it with the SQLite-only option the README describes.
  • QDRANT_API_KEY is needed for Qdrant Cloud, and FASTEMBED_MODEL selects the embedding model.
  • Apache 2.0 licensed, and a v0.2.0 rebuild is in progress.

Setup effort

Build from source — git clone https://github.com/ChrisGVE/workspace-qdrant-mcp.git

See installation options