Skip to main content
Glama
RyanLisse

LanceDB MCP Server

by RyanLisse

Servidor MCP de LanceDB

Descripción general

Implementación de un servidor del Protocolo de Contexto de Modelo (MCP) para operaciones con la base de datos vectorial LanceDB. Este servidor permite el almacenamiento eficiente de vectores, la búsqueda por similitud y la gestión de incrustaciones vectoriales con sus metadatos asociados.

Related MCP server: KGrag MCP Server

Componentes

Recursos

El servidor expone las tablas de bases de datos vectoriales como recursos:

  • table://{name} : Una tabla de base de datos vectorial que almacena incrustaciones y metadatos

    • Dimensiones vectoriales configurables

    • Compatibilidad con metadatos de texto

    • Capacidades eficientes de búsqueda de similitud

Puntos finales de API

Gestión de tablas

  • POST /table

    • Crear una nueva tabla de vectores

    • Aporte:

      {
        "name": "my_table",      # Table name
        "dimension": 768         # Vector dimension
      }

Operaciones vectoriales

  • POST /table/{table_name}/vector

    • Agregar datos vectoriales a una tabla

    • Aporte:

      {
        "vector": [0.1, 0.2, ...],  # Vector data
        "text": "associated text"    # Metadata
      }
  • POST /table/{table_name}/search

    • Buscar vectores similares

    • Aporte:

      {
        "vector": [0.1, 0.2, ...],  # Query vector
        "limit": 10                  # Number of results
      }

Instalación

# Clone the repository
git clone https://github.com/yourusername/lancedb_mcp.git
cd lancedb_mcp

# Install dependencies using uv
uv pip install -e .

Uso con Claude Desktop

# Add the server to your claude_desktop_config.json
"mcpServers": {
  "lancedb": {
    "command": "uv",
    "args": [
      "run",
      "python",
      "-m",
      "lancedb_mcp",
      "--db-path",
      "~/.lancedb"
    ]
  }
}

Desarrollo

# Install development dependencies
uv pip install -e ".[dev]"

# Run tests
pytest

# Format code
black .
ruff .

Variables de entorno

  • LANCEDB_URI : Ruta de almacenamiento de LanceDB (valor predeterminado: ".lancedb")

Licencia

Este proyecto está licenciado bajo la Licencia MIT. Consulte el archivo de LICENCIA para más detalles.

F
license - not found
Not graded
quality - not tested
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables seamless integration with Weaviate vector databases, providing tools for semantic, keyword, and hybrid search across local or cloud instances. It supports schema management, collection retrieval, and multi-tenancy configurations through the Model Context Protocol.
    5
    MIT
  • F
    license
    Not graded
    quality
    B
    maintenance
    Enables natural-language querying of structured data via Model Context Protocol, allowing AI agents to answer questions without SQL or API knowledge.

View all related MCP servers

Related MCP Connectors

  • Universal memory for AI agents and tools. Save, organize and search context anywhere.

  • Your portable context layer — load it into any AI.

  • Mem0-compatible persistent memory for AI agents: write facts once, recall them semantically.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/RyanLisse/lancedb_mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server