Skip to main content
Glama

workspace-qdrant-mcp

License: MIT GitHub Release Glama Homebrew TypeScript Rust Qdrant

Base de datos vectorial con alcance de proyecto para asistentes de IA, que proporciona búsqueda semántica + por palabras clave híbrida con detección automática de proyectos.

Características

  • Búsqueda híbrida - Combina similitud semántica con coincidencia de palabras clave utilizando Reciprocal Rank Fusion (RRF).

  • Detección de proyectos - Reconocimiento automático de repositorios Git y colecciones con alcance de proyecto.

  • 6 herramientas MCP - search, retrieve, rules, store, grep, list.

  • Inteligencia de código - Fragmentación semántica con Tree-sitter + integración LSP para proyectos activos.

  • Grafo de código - Grafo de relaciones con algoritmos (PageRank, detección de comunidades, centralidad de intermediación).

  • CLI de alto rendimiento - Herramienta de línea de comandos wqm basada en Rust.

  • Daemon en segundo plano - memexd para la supervisión y procesamiento continuo de archivos.

Related MCP server: Super-Memory-TS

Inicio rápido

Requisitos previos

  • Qdrant - docker run -d -p 6333:6333 -v qdrant_storage:/qdrant/storage qdrant/qdrant

  • Compilador C - Requerido para compilar gramáticas de Tree-sitter en el primer uso. Las gramáticas de Tree-sitter se distribuyen como código fuente C y se compilan localmente.

    • macOS: xcode-select --install (Herramientas de línea de comandos de Xcode)

    • Linux: apt install build-essential (Debian/Ubuntu) o dnf groupinstall "Development Tools" (Fedora)

    • Windows: Instala Visual Studio Build Tools con la carga de trabajo de C++.

Instalación

Opción 1: Homebrew (Recomendado — macOS y Linux)

brew install ChrisGVE/tap/workspace-qdrant
brew services start workspace-qdrant

Opción 2: Binarios precompilados

# macOS / Linux
curl -fsSL https://raw.githubusercontent.com/ChrisGVE/workspace-qdrant-mcp/main/scripts/download-install.sh | bash

# Windows (PowerShell)
irm https://raw.githubusercontent.com/ChrisGVE/workspace-qdrant-mcp/main/scripts/download-install.ps1 | iex

Instala wqm y memexd en ~/.local/bin (Linux/macOS) o %LOCALAPPDATA%\wqm\bin (Windows).

Opción 3: Compilar desde el código fuente

git clone https://github.com/ChrisGVE/workspace-qdrant-mcp.git
cd workspace-qdrant-mcp
./install.sh

Consulta la Referencia de instalación para obtener instrucciones detalladas y notas específicas de la plataforma. Para Windows, consulta la Guía de instalación de Windows.

Configurar MCP

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "workspace-qdrant-mcp": {
      "command": "node",
      "args": ["/path/to/workspace-qdrant-mcp/src/typescript/mcp-server/dist/index.js"],
      "env": {
        "QDRANT_URL": "http://localhost:6333"
      }
    }
  }
}

Claude Code:

claude mcp add workspace-qdrant-mcp -- node /path/to/workspace-qdrant-mcp/src/typescript/mcp-server/dist/index.js

Verificar

wqm --version
wqm status health

Integración con CLAUDE.md

Añade lo siguiente al archivo CLAUDE.md de tu proyecto (o a tu ~/.claude/CLAUDE.md global) para que Claude Code utilice workspace-qdrant de forma proactiva:

## workspace-qdrant

The `workspace-qdrant` MCP server provides codebase-aware search, a library knowledge base, a scratchpad for accumulated insights, and persistent behavioral rules. The tool schemas are self-describing; these instructions cover *when* and *how* to use them.

### Primary Search and Knowledge Base

**Use `workspace-qdrant` first whenever context is uncertain** — first session on a project, returning after a significant gap, or exploring an unfamiliar subsystem. It is faster and more accurate than walking files manually, and it retrieves findings from prior sessions that would otherwise be lost.

**Three-step protocol:**
1. **Search** with `workspace-qdrant` (`search`, `grep`, `list`, or `retrieve`)
2. **Fall back** to `Grep`, `Glob`, `WebSearch` only when workspace-qdrant is insufficient or unavailable
3. **Store** any new findings, analysis, or design rationale via `store` so they are retrievable in future sessions

When a fresh handover or strong prior context already covers what you need, skip the exploratory search — but always store new findings at the end.

**Collections and their purpose:**
- `projects` — indexed codebase; use `scope="project"` (current project) or `scope="all"` (across all projects)
- `libraries` — external reference docs, API specs, third-party documentation; add via `store` with `collection="libraries"` and search with `includeLibraries=true`
- `scratchpad` — analysis, design rationale, research transcripts, architectural insights; complements session handovers by building a growing, semantically searchable knowledge layer across sessions
- `rules` — persistent behavioral rules; load at session start via `rules` → `action="list"`

**Practical notes:**
- Use `grep` for exact strings or regex; `list` with `format="summary"` to explore project structure
- Store external docs or specs into `libraries` so they are searchable alongside code
- Use the scratchpad to record *why* decisions were made, not just *what* was done — future sessions can retrieve the reasoning

### Sub-Agents

Sub-agents start with only the prompt you give them — they have no session history or handover context. They must always use `workspace-qdrant` first for any code exploration, without exception. Include this verbatim in every agent prompt:

> "You have no prior context about this codebase. Use `workspace-qdrant` as your mandatory first tool for ALL code searches — symbols, functions, architecture, patterns, prior findings. Use `search`, `grep`, `list`, or `retrieve` before touching any file with Read/Grep/Glob. Store any new findings, analysis, or design rationale via `store` (scratchpad for insights, libraries for reference docs) so they persist for future sessions."

### Project Registration

At session start, check whether the current project is registered with workspace-qdrant. If it is not, ask the user whether they want to register it (do not register silently). Once registered, the daemon handles file watching and ingestion automatically — no further action is needed.

### Behavioral Rules

The `rules` tool manages persistent rules that are injected into context across sessions. Rules are **user-initiated only** — add rules when the user explicitly instructs you to, never autonomously. Use `action="list"` at session start to load active rules.

### Issue Reporting

workspace-qdrant is under active development. If you encounter errors, unexpected behavior, or limitations with any workspace-qdrant tool, report them as GitHub issues at https://github.com/ChrisGVE/workspace-qdrant-mcp/issues using the `gh` CLI.

Herramientas MCP

Herramienta

Propósito

search

Búsqueda híbrida semántica + por palabras clave en el contenido indexado

retrieve

Búsqueda directa de documentos por ID o filtro de metadatos

rules

Gestionar reglas de comportamiento persistentes

store

Almacenar contenido, registrar proyectos, guardar notas

grep

Búsqueda exacta de subcadenas o expresiones regulares usando FTS5

list

Listar archivos del proyecto y estructura de carpetas

Consulta la Referencia de herramientas MCP para ver parámetros y ejemplos.

Colecciones

Colección

Propósito

Aislamiento

projects

Código y documentación del proyecto

Multi-inquilino por tenant_id

libraries

Documentación de referencia (libros, artículos, docs)

Multi-inquilino por library_name

rules

Reglas de comportamiento y preferencias

Multi-inquilino por project_id

scratchpad

Almacenamiento de trabajo temporal

Por sesión

Referencia de la CLI

# Service management
wqm service start              # Start background daemon
wqm service status             # Check daemon status
wqm status health              # System health check

# Search and content
wqm search "query"             # Search collections
wqm ingest file path.py        # Ingest a file
wqm rules list                 # List behavioral rules

# Project and library
wqm project list               # List registered projects
wqm project watch pause        # Pause file watchers
wqm library list               # List libraries
wqm tags list                  # List tags with counts

# Administration
wqm admin collections list     # List collections
wqm admin rebuild all          # Rebuild all indexes
wqm admin backup create        # Backup snapshots
wqm admin stats overview       # Search analytics

# Code graph
wqm graph stats --tenant <t>   # Node/edge counts
wqm graph query --node-id <id> --tenant <t> --hops 2   # Related nodes
wqm graph impact --symbol <name> --tenant <t>           # Impact analysis
wqm graph pagerank --tenant <t> --top-k 20              # PageRank centrality

# Setup
wqm init completions zsh       # Shell completions
wqm init man install           # Install man pages
wqm init hooks install         # Install Claude Code hooks

# Queue and monitoring
wqm queue stats                # Queue statistics

Consulta la Referencia de la CLI para obtener la documentación completa.

Configuración

Variables de entorno

Variable

Predeterminado

Descripción

QDRANT_URL

http://localhost:6333

URL del servidor Qdrant

QDRANT_API_KEY

-

Clave de API (requerida para Qdrant Cloud)

FASTEMBED_MODEL

all-MiniLM-L6-v2

Modelo de incrustación (embedding)

Arquitectura

                    +-----------------+
                    |  Claude/Client  |
                    +--------+--------+
                             |
                    +--------v--------+
                    |   MCP Server    |  (TypeScript)
                    +--------+--------+
                             |
              +--------------+--------------+
              |                             |
     +--------v--------+           +--------v--------+
     |   Rust Daemon   |           |     Qdrant      |
     |    (memexd)     |           | Vector Database |
     +--------+--------+           +-----------------+
              |
     +--------v--------+
     |  File Watcher   |
     |  Code Graph     |
     |  Embeddings     |
     +-----------------+

El daemon de Rust gestiona la supervisión de archivos, la generación de incrustaciones, la extracción del grafo de código y el procesamiento de colas. Todas las escrituras se dirigen a través del daemon para garantizar la consistencia.

Documentación

Guías de usuario:

Referencia:

Consulta el Índice de documentación para especificaciones, ADRs y recursos para desarrolladores.

Desarrollo

# TypeScript MCP server
cd src/typescript/mcp-server && npm install && npm run build && npm test

# Rust daemon and CLI (from src/rust/)
cargo build --release
cargo test

# Graph benchmarks
cargo bench --package workspace-qdrant-core --bench graph_bench

# Binaries output to:
# - target/release/wqm
# - target/release/memexd

Contribución

Consulta CONTRIBUTING.md para la configuración de desarrollo y las directrices.

Licencia

Licencia MIT - consulta LICENSE para más detalles.


Inspirado en claude-qdrant-mcp

Available Tools

6 tools
grepB

Search code with exact substring or regex pattern matching. Uses FTS5 trigram index for fast line-level search across indexed files.

Inputs: pattern (required), regex, caseSensitive, pathGlob, +5 more.

listA

List project files and folder structure. Shows only indexed files (excludes gitignored, node_modules, etc). Use format "summary" first to understand project layout, then drill into specific folders with the path parameter.

Inputs: path, depth, format, fileType, +7 more.

retrieveA

Retrieve documents by ID or metadata filter. Use this to access specific documents when you know the document ID. Prefer search for discovery, retrieve for known documents.

Inputs: documentId, collection, filter, limit, +3 more.

rulesA

Manage behavioral rules (add, update, remove, list). Check active rules at the start of each session to load the user's behavioral preferences. Rules persist across sessions and guide how you should work.

Inputs: action (required), content, label, scope, +5 more.

storeA

Store content or register a project. Use type "library" (default) to store reference documentation, type "url" to fetch and ingest a web page, type "scratchpad" to save persistent notes/scratch space, or type "project" to register a project directory for file watching and ingestion.

Inputs: type, content, libraryName, forProject, +8 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool targets a distinct function: grep searches code lines, list navigates files, retrieve fetches known documents, rules manages preferences, search discovers content, and store ingests content. There is no functional overlap.

    Naming Consistency5/5

    All tool names are single lowercase verbs (grep, list, retrieve, rules, search, store), following a consistent and predictable pattern.

    Tool Count5/5

    With 6 tools covering searching, navigation, retrieval, storage, and rule management, the count is well-scoped for a workspace knowledge server without being excessive or sparse.

    Completeness4/5

    The tool surface covers the core workflows of searching, browsing, retrieving, storing, and managing rules. One minor gap is the lack of explicit update/delete operations for stored documents, though store may allow overwriting.

    Maintenance

    ActivitySlowing
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Persistent knowledge memory layer for AI agents. Hybrid semantic + full-text search with pgvector, code dependency graph with blast-radius impact analysis, and incremental indexing for 7 languages. In-process ONNX embeddings, no external API required.
      47 PyPI
      34
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Local-first semantic memory server with project indexing for AI assistants. It enables AI assistants to store, retrieve, and search memories and project code using embeddings and vector search.
      68 npm
      MIT