# QDrant Loader MCP Server
[](https://pypi.org/project/qdrant-loader-mcp-server/)
[](https://pypi.org/project/qdrant-loader-mcp-server/)
[](https://www.gnu.org/licenses/gpl-3.0)
A Model Context Protocol (MCP) server that provides advanced Retrieval-Augmented Generation (RAG) capabilities to AI development tools. Part of the [QDrant Loader monorepo](../../) ecosystem.
## 🚀 What It Does
The MCP Server bridges your QDrant knowledge base with AI development tools:
- **Provides intelligent search** through semantic, hierarchy-aware, and attachment-focused tools
- **Integrates seamlessly** with Cursor, Windsurf, Claude Desktop, and other MCP-compatible tools
- **Understands context** including document hierarchies, file relationships, and metadata
- **Streams responses** for fast, real-time search results
- **Preserves relationships** between documents, attachments, and parent content
## 🔌 Supported AI Tools
| Tool | Status | Integration Features |
|------|--------|---------------------|
| **Cursor** | ✅ Full Support | Context-aware code assistance, documentation lookup, intelligent suggestions |
| **Windsurf** | ✅ Compatible | MCP protocol integration, semantic search capabilities |
| **Claude Desktop** | ✅ Compatible | Direct MCP integration, conversational search interface |
| **Other MCP Tools** | ✅ Compatible | Any tool supporting MCP 2024-11-05 specification |
## 🔍 Advanced Search Capabilities
### Three Specialized Search Tools
#### 1. `search` - Universal Semantic Search
- **Purpose**: General-purpose semantic search across all content
- **Best for**: Finding relevant information by meaning, not just keywords
- **Features**: Multi-source search, relevance ranking, context preservation
#### 2. `hierarchy_search` - Confluence-Aware Search
- **Purpose**: Confluence-specific search with deep hierarchy understanding
- **Best for**: Navigating complex documentation structures, finding related pages
- **Features**: Parent/child relationships, breadcrumb paths, hierarchy filtering
#### 3. `attachment_search` - File-Focused Search
- **Purpose**: Finding files and attachments with parent document context
- **Best for**: Locating specific files, templates, specifications, or supporting materials
- **Features**: File type filtering, size filtering, parent document relationships
### Search Intelligence Features
- **Hierarchy Understanding**: Recognizes parent/child page relationships in Confluence
- **Attachment Awareness**: Connects files to their parent documents and context
- **Metadata Enrichment**: Includes authors, dates, file sizes, and source information
- **Visual Indicators**: Rich formatting with icons and context clues
- **Relationship Mapping**: Shows connections between related content
## 📦 Installation
### From PyPI (Recommended)
```bash
pip install qdrant-loader-mcp-server
```
### From Source (Development)
```bash
# Clone the monorepo
git clone https://github.com/martin-papy/qdrant-loader.git
cd qdrant-loader
# Install in development mode
pip install -e packages/qdrant-loader-mcp-server[dev]
```
### Complete RAG Pipeline
For full functionality with data ingestion:
```bash
# Install both packages
pip install qdrant-loader qdrant-loader-mcp-server
```
## ⚡ Quick Start
### 1. Environment Setup
```bash
# Required environment variables
export QDRANT_URL="http://localhost:6333"
export QDRANT_API_KEY="your_api_key" # Required for QDrant Cloud
export OPENAI_API_KEY="your_openai_key"
# Optional configuration
export QDRANT_COLLECTION_NAME="documents" # Default collection name
export MCP_LOG_LEVEL="INFO" # Logging level
export MCP_LOG_FILE="/path/to/mcp.log" # Log file path
export MCP_DISABLE_CONSOLE_LOGGING="true" # Recommended for Cursor
```
### 2. Start the Server
```bash
# Start MCP server
mcp-qdrant-loader
# With debug logging
mcp-qdrant-loader --log-level DEBUG
# Show help
mcp-qdrant-loader --help
```
### 3. Test the Connection
```bash
# Test with a simple search
echo '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search","arguments":{"query":"test","limit":1}}}' | mcp-qdrant-loader
```
## 🔧 Configuration
### Environment Variables
| Variable | Description | Default | Required |
|----------|-------------|---------|----------|
| `QDRANT_URL` | QDrant instance URL | `http://localhost:6333` | Yes |
| `QDRANT_API_KEY` | QDrant API key | None | Cloud only |
| `QDRANT_COLLECTION_NAME` | Collection name | `documents` | No |
| `OPENAI_API_KEY` | OpenAI API key for embeddings | None | Yes |
| `MCP_LOG_LEVEL` | Logging level | `INFO` | No |
| `MCP_LOG_FILE` | Log file path | None | No |
| `MCP_DISABLE_CONSOLE_LOGGING` | Disable console output | `false` | **Yes for Cursor** |
### Important Configuration Notes
- **For Cursor Integration**: Always set `MCP_DISABLE_CONSOLE_LOGGING=true` to prevent interference with JSON-RPC communication
- **For Debugging**: Use `MCP_LOG_FILE` to write logs when console logging is disabled
- **API Keys**: OpenAI API keys should start with `sk-proj-` for project keys or `sk-` for user keys
## 🎯 AI Tool Integration
### Cursor IDE Integration
Add to your `.cursor/mcp.json`:
```json
{
"mcpServers": {
"qdrant-loader": {
"command": "/path/to/venv/bin/mcp-qdrant-loader",
"env": {
"QDRANT_URL": "http://localhost:6333",
"QDRANT_API_KEY": "your_qdrant_api_key",
"OPENAI_API_KEY": "sk-proj-your_openai_api_key",
"QDRANT_COLLECTION_NAME": "your_collection",
"MCP_LOG_LEVEL": "INFO",
"MCP_LOG_FILE": "/path/to/logs/mcp.log",
"MCP_DISABLE_CONSOLE_LOGGING": "true"
}
}
}
}
```
### Windsurf Integration
Similar configuration in Windsurf's MCP settings:
```json
{
"mcp": {
"servers": {
"qdrant-loader": {
"command": "/path/to/venv/bin/mcp-qdrant-loader",
"env": {
"QDRANT_URL": "http://localhost:6333",
"OPENAI_API_KEY": "your_openai_key",
"MCP_DISABLE_CONSOLE_LOGGING": "true"
}
}
}
}
}
```
### Claude Desktop Integration
Add to Claude Desktop's configuration:
```json
{
"mcpServers": {
"qdrant-loader": {
"command": "/path/to/venv/bin/mcp-qdrant-loader",
"env": {
"QDRANT_URL": "http://localhost:6333",
"OPENAI_API_KEY": "your_openai_key"
}
}
}
}
```
## 🎯 Usage Examples
### In Cursor IDE
Ask your AI assistant:
- *"Find documentation about authentication in our API"*
- *"Show me examples of error handling patterns in our codebase"*
- *"What are the deployment requirements for this service?"*
- *"Find all PDF attachments related to database schema"*
- *"Show me the hierarchy of pages under the Architecture section"*
### Advanced Search Queries
#### Semantic Search
```
Find information about rate limiting implementation
```
#### Hierarchy Search
```
Show me all child pages under the API Documentation section
```
#### Attachment Search
```
Find all Excel files uploaded by john.doe in the last month
```
## 🏗️ Architecture
### MCP Protocol Implementation
- **Full MCP 2024-11-05 compliance** with proper JSON-RPC communication
- **Tool registration** for search, hierarchy_search, and attachment_search
- **Streaming responses** for large result sets
- **Error handling** with proper MCP error codes
- **Resource management** for efficient memory usage
### Search Engine Components
- **Embedding Service**: Generates query embeddings using OpenAI
- **Vector Search**: Performs semantic similarity search in QDrant
- **Metadata Processor**: Enriches results with hierarchy and attachment information
- **Result Formatter**: Creates rich, contextual response formatting
- **Caching Layer**: Optimizes performance for repeated queries
### Data Flow
```text
AI Tool → MCP Server → QDrant Search → Result Processing → Formatted Response
↓ ↓ ↓ ↓ ↓
Cursor JSON-RPC Vector Query Metadata Rich Context
Windsurf Protocol Embedding Enrichment Visual Indicators
Claude Tool Call Similarity Hierarchy Relationship Info
Other Streaming Ranking Attachments Source Attribution
```
## 🔍 Search Tool Details
### Universal Search (`search`)
**Parameters:**
- `query` (required): Natural language search query
- `limit` (optional): Maximum number of results (default: 5)
- `source_types` (optional): Filter by source types (git, confluence, jira, etc.)
**Example:**
```json
{
"name": "search",
"arguments": {
"query": "authentication implementation",
"limit": 10,
"source_types": ["git", "confluence"]
}
}
```
### Hierarchy Search (`hierarchy_search`)
**Parameters:**
- `query` (required): Search query
- `limit` (optional): Maximum results (default: 10)
- `organize_by_hierarchy` (optional): Group results by hierarchy (default: false)
- `hierarchy_filter` (optional): Filter options:
- `root_only`: Show only root pages
- `depth`: Filter by hierarchy depth
- `parent_title`: Filter by parent page title
- `has_children`: Filter by whether pages have children
**Example:**
```json
{
"name": "hierarchy_search",
"arguments": {
"query": "API documentation",
"organize_by_hierarchy": true,
"hierarchy_filter": {
"depth": 2,
"has_children": true
}
}
}
```
### Attachment Search (`attachment_search`)
**Parameters:**
- `query` (required): Search query
- `limit` (optional): Maximum results (default: 10)
- `include_parent_context` (optional): Include parent document info (default: true)
- `attachment_filter` (optional): Filter options:
- `attachments_only`: Show only attachments
- `file_type`: Filter by file extension
- `file_size_min`/`file_size_max`: Size range filtering
- `author`: Filter by attachment author
- `parent_document_title`: Filter by parent document
**Example:**
```json
{
"name": "attachment_search",
"arguments": {
"query": "database schema",
"attachment_filter": {
"file_type": "pdf",
"file_size_min": 1024
}
}
}
```
## 🧪 Testing
```bash
# Run all tests
pytest packages/qdrant-loader-mcp-server/tests/
# Run with coverage
pytest --cov=qdrant_loader_mcp_server packages/qdrant-loader-mcp-server/tests/
# Test MCP protocol compliance
pytest -m "mcp" packages/qdrant-loader-mcp-server/tests/
```
## 🤝 Contributing
This package is part of the QDrant Loader monorepo. See the [main contributing guide](../../CONTRIBUTING.md) for details.
### Development Setup
```bash
# Clone and setup
git clone https://github.com/martin-papy/qdrant-loader.git
cd qdrant-loader
# Install in development mode
pip install -e packages/qdrant-loader-mcp-server[dev]
# Run tests
pytest packages/qdrant-loader-mcp-server/tests/
```
## 📚 Documentation
- **[Complete Documentation](../../docs/)** - Comprehensive guides and references
- **[Getting Started](../../docs/getting-started/)** - Quick start and core concepts
- **[MCP Server Guide](../../docs/users/detailed-guides/mcp-server/)** - Detailed MCP server documentation
- **[Developer Docs](../../docs/developers/)** - Architecture and API reference
## 🆘 Support
- **[Issues](https://github.com/martin-papy/qdrant-loader/issues)** - Bug reports and feature requests
- **[Discussions](https://github.com/martin-papy/qdrant-loader/discussions)** - Community Q&A
- **[Documentation](../../docs/)** - Comprehensive guides
## 📄 License
This project is licensed under the GNU GPLv3 - see the [LICENSE](../../LICENSE) file for details.
---
**Ready to supercharge your AI development?** Check out the [MCP Server Guide](../../docs/users/detailed-guides/mcp-server/) or explore the [complete documentation](../../docs/).
Raw data
{
"_id": null,
"home_page": null,
"name": "qdrant-loader-mcp-server",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.12",
"maintainer_email": null,
"keywords": "qdrant, vector-database, mcp, cursor, rag, embeddings, multi-project, semantic-search",
"author": null,
"author_email": "Martin Papy <martin.papy@cbtw.tech>",
"download_url": "https://files.pythonhosted.org/packages/35/34/5197fe382799e37ad83d0b2c4efa4473b2fd22d78deec41a6d3ffd7b7a6e/qdrant_loader_mcp_server-0.4.13.tar.gz",
"platform": null,
"description": "# QDrant Loader MCP Server\n\n[](https://pypi.org/project/qdrant-loader-mcp-server/)\n[](https://pypi.org/project/qdrant-loader-mcp-server/)\n[](https://www.gnu.org/licenses/gpl-3.0)\n\nA Model Context Protocol (MCP) server that provides advanced Retrieval-Augmented Generation (RAG) capabilities to AI development tools. Part of the [QDrant Loader monorepo](../../) ecosystem.\n\n## \ud83d\ude80 What It Does\n\nThe MCP Server bridges your QDrant knowledge base with AI development tools:\n\n- **Provides intelligent search** through semantic, hierarchy-aware, and attachment-focused tools\n- **Integrates seamlessly** with Cursor, Windsurf, Claude Desktop, and other MCP-compatible tools\n- **Understands context** including document hierarchies, file relationships, and metadata\n- **Streams responses** for fast, real-time search results\n- **Preserves relationships** between documents, attachments, and parent content\n\n## \ud83d\udd0c Supported AI Tools\n\n| Tool | Status | Integration Features |\n|------|--------|---------------------|\n| **Cursor** | \u2705 Full Support | Context-aware code assistance, documentation lookup, intelligent suggestions |\n| **Windsurf** | \u2705 Compatible | MCP protocol integration, semantic search capabilities |\n| **Claude Desktop** | \u2705 Compatible | Direct MCP integration, conversational search interface |\n| **Other MCP Tools** | \u2705 Compatible | Any tool supporting MCP 2024-11-05 specification |\n\n## \ud83d\udd0d Advanced Search Capabilities\n\n### Three Specialized Search Tools\n\n#### 1. `search` - Universal Semantic Search\n\n- **Purpose**: General-purpose semantic search across all content\n- **Best for**: Finding relevant information by meaning, not just keywords\n- **Features**: Multi-source search, relevance ranking, context preservation\n\n#### 2. `hierarchy_search` - Confluence-Aware Search\n\n- **Purpose**: Confluence-specific search with deep hierarchy understanding\n- **Best for**: Navigating complex documentation structures, finding related pages\n- **Features**: Parent/child relationships, breadcrumb paths, hierarchy filtering\n\n#### 3. `attachment_search` - File-Focused Search\n\n- **Purpose**: Finding files and attachments with parent document context\n- **Best for**: Locating specific files, templates, specifications, or supporting materials\n- **Features**: File type filtering, size filtering, parent document relationships\n\n### Search Intelligence Features\n\n- **Hierarchy Understanding**: Recognizes parent/child page relationships in Confluence\n- **Attachment Awareness**: Connects files to their parent documents and context\n- **Metadata Enrichment**: Includes authors, dates, file sizes, and source information\n- **Visual Indicators**: Rich formatting with icons and context clues\n- **Relationship Mapping**: Shows connections between related content\n\n## \ud83d\udce6 Installation\n\n### From PyPI (Recommended)\n\n```bash\npip install qdrant-loader-mcp-server\n```\n\n### From Source (Development)\n\n```bash\n# Clone the monorepo\ngit clone https://github.com/martin-papy/qdrant-loader.git\ncd qdrant-loader\n\n# Install in development mode\npip install -e packages/qdrant-loader-mcp-server[dev]\n```\n\n### Complete RAG Pipeline\n\nFor full functionality with data ingestion:\n\n```bash\n# Install both packages\npip install qdrant-loader qdrant-loader-mcp-server\n```\n\n## \u26a1 Quick Start\n\n### 1. Environment Setup\n\n```bash\n# Required environment variables\nexport QDRANT_URL=\"http://localhost:6333\"\nexport QDRANT_API_KEY=\"your_api_key\" # Required for QDrant Cloud\nexport OPENAI_API_KEY=\"your_openai_key\"\n\n# Optional configuration\nexport QDRANT_COLLECTION_NAME=\"documents\" # Default collection name\nexport MCP_LOG_LEVEL=\"INFO\" # Logging level\nexport MCP_LOG_FILE=\"/path/to/mcp.log\" # Log file path\nexport MCP_DISABLE_CONSOLE_LOGGING=\"true\" # Recommended for Cursor\n```\n\n### 2. Start the Server\n\n```bash\n# Start MCP server\nmcp-qdrant-loader\n\n# With debug logging\nmcp-qdrant-loader --log-level DEBUG\n\n# Show help\nmcp-qdrant-loader --help\n```\n\n### 3. Test the Connection\n\n```bash\n# Test with a simple search\necho '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"tools/call\",\"params\":{\"name\":\"search\",\"arguments\":{\"query\":\"test\",\"limit\":1}}}' | mcp-qdrant-loader\n```\n\n## \ud83d\udd27 Configuration\n\n### Environment Variables\n\n| Variable | Description | Default | Required |\n|----------|-------------|---------|----------|\n| `QDRANT_URL` | QDrant instance URL | `http://localhost:6333` | Yes |\n| `QDRANT_API_KEY` | QDrant API key | None | Cloud only |\n| `QDRANT_COLLECTION_NAME` | Collection name | `documents` | No |\n| `OPENAI_API_KEY` | OpenAI API key for embeddings | None | Yes |\n| `MCP_LOG_LEVEL` | Logging level | `INFO` | No |\n| `MCP_LOG_FILE` | Log file path | None | No |\n| `MCP_DISABLE_CONSOLE_LOGGING` | Disable console output | `false` | **Yes for Cursor** |\n\n### Important Configuration Notes\n\n- **For Cursor Integration**: Always set `MCP_DISABLE_CONSOLE_LOGGING=true` to prevent interference with JSON-RPC communication\n- **For Debugging**: Use `MCP_LOG_FILE` to write logs when console logging is disabled\n- **API Keys**: OpenAI API keys should start with `sk-proj-` for project keys or `sk-` for user keys\n\n## \ud83c\udfaf AI Tool Integration\n\n### Cursor IDE Integration\n\nAdd to your `.cursor/mcp.json`:\n\n```json\n{\n \"mcpServers\": {\n \"qdrant-loader\": {\n \"command\": \"/path/to/venv/bin/mcp-qdrant-loader\",\n \"env\": {\n \"QDRANT_URL\": \"http://localhost:6333\",\n \"QDRANT_API_KEY\": \"your_qdrant_api_key\",\n \"OPENAI_API_KEY\": \"sk-proj-your_openai_api_key\",\n \"QDRANT_COLLECTION_NAME\": \"your_collection\",\n \"MCP_LOG_LEVEL\": \"INFO\",\n \"MCP_LOG_FILE\": \"/path/to/logs/mcp.log\",\n \"MCP_DISABLE_CONSOLE_LOGGING\": \"true\"\n }\n }\n }\n}\n```\n\n### Windsurf Integration\n\nSimilar configuration in Windsurf's MCP settings:\n\n```json\n{\n \"mcp\": {\n \"servers\": {\n \"qdrant-loader\": {\n \"command\": \"/path/to/venv/bin/mcp-qdrant-loader\",\n \"env\": {\n \"QDRANT_URL\": \"http://localhost:6333\",\n \"OPENAI_API_KEY\": \"your_openai_key\",\n \"MCP_DISABLE_CONSOLE_LOGGING\": \"true\"\n }\n }\n }\n }\n}\n```\n\n### Claude Desktop Integration\n\nAdd to Claude Desktop's configuration:\n\n```json\n{\n \"mcpServers\": {\n \"qdrant-loader\": {\n \"command\": \"/path/to/venv/bin/mcp-qdrant-loader\",\n \"env\": {\n \"QDRANT_URL\": \"http://localhost:6333\",\n \"OPENAI_API_KEY\": \"your_openai_key\"\n }\n }\n }\n}\n```\n\n## \ud83c\udfaf Usage Examples\n\n### In Cursor IDE\n\nAsk your AI assistant:\n\n- *\"Find documentation about authentication in our API\"*\n- *\"Show me examples of error handling patterns in our codebase\"*\n- *\"What are the deployment requirements for this service?\"*\n- *\"Find all PDF attachments related to database schema\"*\n- *\"Show me the hierarchy of pages under the Architecture section\"*\n\n### Advanced Search Queries\n\n#### Semantic Search\n\n```\nFind information about rate limiting implementation\n```\n\n#### Hierarchy Search\n\n```\nShow me all child pages under the API Documentation section\n```\n\n#### Attachment Search\n\n```\nFind all Excel files uploaded by john.doe in the last month\n```\n\n## \ud83c\udfd7\ufe0f Architecture\n\n### MCP Protocol Implementation\n\n- **Full MCP 2024-11-05 compliance** with proper JSON-RPC communication\n- **Tool registration** for search, hierarchy_search, and attachment_search\n- **Streaming responses** for large result sets\n- **Error handling** with proper MCP error codes\n- **Resource management** for efficient memory usage\n\n### Search Engine Components\n\n- **Embedding Service**: Generates query embeddings using OpenAI\n- **Vector Search**: Performs semantic similarity search in QDrant\n- **Metadata Processor**: Enriches results with hierarchy and attachment information\n- **Result Formatter**: Creates rich, contextual response formatting\n- **Caching Layer**: Optimizes performance for repeated queries\n\n### Data Flow\n\n```text\nAI Tool \u2192 MCP Server \u2192 QDrant Search \u2192 Result Processing \u2192 Formatted Response\n \u2193 \u2193 \u2193 \u2193 \u2193\nCursor JSON-RPC Vector Query Metadata Rich Context\nWindsurf Protocol Embedding Enrichment Visual Indicators\nClaude Tool Call Similarity Hierarchy Relationship Info\nOther Streaming Ranking Attachments Source Attribution\n```\n\n## \ud83d\udd0d Search Tool Details\n\n### Universal Search (`search`)\n\n**Parameters:**\n\n- `query` (required): Natural language search query\n- `limit` (optional): Maximum number of results (default: 5)\n- `source_types` (optional): Filter by source types (git, confluence, jira, etc.)\n\n**Example:**\n\n```json\n{\n \"name\": \"search\",\n \"arguments\": {\n \"query\": \"authentication implementation\",\n \"limit\": 10,\n \"source_types\": [\"git\", \"confluence\"]\n }\n}\n```\n\n### Hierarchy Search (`hierarchy_search`)\n\n**Parameters:**\n\n- `query` (required): Search query\n- `limit` (optional): Maximum results (default: 10)\n- `organize_by_hierarchy` (optional): Group results by hierarchy (default: false)\n- `hierarchy_filter` (optional): Filter options:\n - `root_only`: Show only root pages\n - `depth`: Filter by hierarchy depth\n - `parent_title`: Filter by parent page title\n - `has_children`: Filter by whether pages have children\n\n**Example:**\n\n```json\n{\n \"name\": \"hierarchy_search\",\n \"arguments\": {\n \"query\": \"API documentation\",\n \"organize_by_hierarchy\": true,\n \"hierarchy_filter\": {\n \"depth\": 2,\n \"has_children\": true\n }\n }\n}\n```\n\n### Attachment Search (`attachment_search`)\n\n**Parameters:**\n\n- `query` (required): Search query\n- `limit` (optional): Maximum results (default: 10)\n- `include_parent_context` (optional): Include parent document info (default: true)\n- `attachment_filter` (optional): Filter options:\n - `attachments_only`: Show only attachments\n - `file_type`: Filter by file extension\n - `file_size_min`/`file_size_max`: Size range filtering\n - `author`: Filter by attachment author\n - `parent_document_title`: Filter by parent document\n\n**Example:**\n\n```json\n{\n \"name\": \"attachment_search\",\n \"arguments\": {\n \"query\": \"database schema\",\n \"attachment_filter\": {\n \"file_type\": \"pdf\",\n \"file_size_min\": 1024\n }\n }\n}\n```\n\n## \ud83e\uddea Testing\n\n```bash\n# Run all tests\npytest packages/qdrant-loader-mcp-server/tests/\n\n# Run with coverage\npytest --cov=qdrant_loader_mcp_server packages/qdrant-loader-mcp-server/tests/\n\n# Test MCP protocol compliance\npytest -m \"mcp\" packages/qdrant-loader-mcp-server/tests/\n```\n\n## \ud83e\udd1d Contributing\n\nThis package is part of the QDrant Loader monorepo. See the [main contributing guide](../../CONTRIBUTING.md) for details.\n\n### Development Setup\n\n```bash\n# Clone and setup\ngit clone https://github.com/martin-papy/qdrant-loader.git\ncd qdrant-loader\n\n# Install in development mode\npip install -e packages/qdrant-loader-mcp-server[dev]\n\n# Run tests\npytest packages/qdrant-loader-mcp-server/tests/\n```\n\n## \ud83d\udcda Documentation\n\n- **[Complete Documentation](../../docs/)** - Comprehensive guides and references\n- **[Getting Started](../../docs/getting-started/)** - Quick start and core concepts\n- **[MCP Server Guide](../../docs/users/detailed-guides/mcp-server/)** - Detailed MCP server documentation\n- **[Developer Docs](../../docs/developers/)** - Architecture and API reference\n\n## \ud83c\udd98 Support\n\n- **[Issues](https://github.com/martin-papy/qdrant-loader/issues)** - Bug reports and feature requests\n- **[Discussions](https://github.com/martin-papy/qdrant-loader/discussions)** - Community Q&A\n- **[Documentation](../../docs/)** - Comprehensive guides\n\n## \ud83d\udcc4 License\n\nThis project is licensed under the GNU GPLv3 - see the [LICENSE](../../LICENSE) file for details.\n\n---\n\n**Ready to supercharge your AI development?** Check out the [MCP Server Guide](../../docs/users/detailed-guides/mcp-server/) or explore the [complete documentation](../../docs/).\n",
"bugtrack_url": null,
"license": null,
"summary": "A Model Context Protocol (MCP) server that provides RAG capabilities to Cursor using Qdrant.",
"version": "0.4.13",
"project_urls": {
"Documentation": "https://qdrant-loader.net/docs/packages/mcp-server/README.html",
"Homepage": "https://qdrant-loader.net",
"Issues": "https://github.com/martin-papy/qdrant-loader/issues",
"Repository": "https://github.com/martin-papy/qdrant-loader"
},
"split_keywords": [
"qdrant",
" vector-database",
" mcp",
" cursor",
" rag",
" embeddings",
" multi-project",
" semantic-search"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "90731edcd9a0ca7a68c72fe675796f523586d15f574be823bf1682a3d66a12ed",
"md5": "2730ecb1fa42853d15fa871052c86ac3",
"sha256": "cbbf52a285ee861788aaf87f799180c0d7adf1eca600554fdcd694cdc6fd7cef"
},
"downloads": -1,
"filename": "qdrant_loader_mcp_server-0.4.13-py3-none-any.whl",
"has_sig": false,
"md5_digest": "2730ecb1fa42853d15fa871052c86ac3",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.12",
"size": 30421,
"upload_time": "2025-07-11T05:22:09",
"upload_time_iso_8601": "2025-07-11T05:22:09.723909Z",
"url": "https://files.pythonhosted.org/packages/90/73/1edcd9a0ca7a68c72fe675796f523586d15f574be823bf1682a3d66a12ed/qdrant_loader_mcp_server-0.4.13-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "35345197fe382799e37ad83d0b2c4efa4473b2fd22d78deec41a6d3ffd7b7a6e",
"md5": "0714b5c68ccf89abca5211c049d45a0b",
"sha256": "f3097c53ba82ba1162f95fea5de93fe4e233d1aa2ad75c6e6a4f941b1ed86d17"
},
"downloads": -1,
"filename": "qdrant_loader_mcp_server-0.4.13.tar.gz",
"has_sig": false,
"md5_digest": "0714b5c68ccf89abca5211c049d45a0b",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.12",
"size": 29823,
"upload_time": "2025-07-11T05:22:11",
"upload_time_iso_8601": "2025-07-11T05:22:11.229286Z",
"url": "https://files.pythonhosted.org/packages/35/34/5197fe382799e37ad83d0b2c4efa4473b2fd22d78deec41a6d3ffd7b7a6e/qdrant_loader_mcp_server-0.4.13.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-11 05:22:11",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "martin-papy",
"github_project": "qdrant-loader",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "qdrant-loader-mcp-server"
}
JSON
