Workspace MCP Server

Code knowledge and metadata with live update, knowledge library, semantic and vector searches

Local serverstdioTypeScript

What is the Workspace MCP server?

Code knowledge and metadata with live update, knowledge library, semantic and vector searches. That is what the workspace mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

Project-scoped vector database for AI assistants, providing hybrid semantic + keyword search with automatic project detection.

  • Hybrid Search — - Combines semantic similarity with keyword matching using Reciprocal Rank Fusion
  • Project Detection — - Automatic Git repository awareness and project-scoped collections
  • 7 MCP Tools — - search, retrieve, rules, store, grep, list, embedding
  • Code Intelligence — - Tree-sitter semantic chunking + LSP integration for active projects
  • Code Graph — - Relationship graph with algorithms (PageRank, community detection, betweenness centrality)
  • High-Performance CLI — - Rust-based wqm command-line tool

Getting it running

Installation goes through your MCP client rather than a global install: point it at qdrant/qdrant on a container image and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

The tools it exposes

The server publishes 8 tools. What each one is for:

  • search — Hybrid semantic + keyword search across indexed content
  • retrieve — Direct document lookup by ID or metadata filter
  • rules — Manage persistent behavioral rules
  • store — Store content, register projects, save notes
  • grep — Exact substring or regex search using FTS5
  • list — List project files and folder structure
  • Prerequisites — The Prerequisites tool exposed by this server
  • Verify — The Verify tool exposed by this server

What it needs from you

Configuration is passed through the environment: QDRANT_URL, CLAUDE_CONFIG_DIR, QDRANT_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  • Qdrant - docker run -d -p 6333:6333 -v qdrant_storage:/qdrant/storage qdrant/qdrant - C compiler - Required for compiling Tree-sitter grammars on first use. Tree-sitter grammars are distributed as C source and compiled locally. - macOS: xcode-select --install (Xcode Command Line Tools) - Linux: apt install build-essential (Debian/Ubuntu) or `dnf groupinstall "Development

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Workspace's toolset — search, retrieve, rules and 5 more — is a fair guide to whether it matches your workflow.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
searchHybrid semantic + keyword search across indexed content
retrieveDirect document lookup by ID or metadata filter
rulesManage persistent behavioral rules
storeStore content, register projects, save notes
grepExact substring or regex search using FTS5
listList project files and folder structure
PrerequisitesThe Prerequisites tool exposed by this server.
VerifyThe Verify tool exposed by this server.

How to install the Workspace MCP server

{
  "mcpServers": {
    "github-com-chrisgve-workspace-qdrant": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "qdrant/qdrant"],
      "env": {
        "QDRANT_URL": "your-value",
        "CLAUDE_CONFIG_DIR": "your-value",
        "QDRANT_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Qdrant - docker run -d -p 6333:6333 -v qdrant_storage:/qdrant/storage qdrant/qdrant - C compiler - Required for compiling Tree-sitter grammars on first use. Tree-sitter grammars are distributed as C source and compiled locally. - macOS: xcode-select --install (Xcode Command Line Tools) - Linux: apt install build-essential (Debian/Ubuntu) or `dnf groupinstall "Development
VariableDescriptionRequired
QDRANT_URLEndpoint or connection string the server talks to.Yes
CLAUDE_CONFIG_DIRFilesystem location the server is allowed to use.Optional
QDRANT_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Workspace to search.
  • Use Workspace to retrieve.
  • Use Workspace to rules.

Frequently asked questions

It connects Workspace to MCP-compatible AI assistants such as Claude and Cursor, exposing 8 tools (search, retrieve, rules, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Workspace directly.