Skip to main content
Glama
Elasticsearch 7.x MCP Server

Elasticsearch 7.x MCP Server

by imlewc

Servidor MCP de Elasticsearch 7.x

insignia de herrería

Un servidor MCP para Elasticsearch 7.x, que proporciona compatibilidad con las versiones de Elasticsearch 7.x.

Características

  • Proporciona una interfaz de protocolo MCP para interactuar con Elasticsearch 7.x

  • Admite operaciones básicas de Elasticsearch (ping, información, etc.)

  • Admite una funcionalidad de búsqueda completa, incluidas consultas de agregación, resaltado, clasificación y otras funciones avanzadas.

  • Acceda fácilmente a la funcionalidad de Elasticsearch a través de cualquier cliente MCP

Related MCP server: Elasticsearch/OpenSearch MCP Server

Requisitos

  • Python 3.10+

  • Elasticsearch 7.x (se recomienda 7.17.x)

Instalación

Instalación mediante herrería

Para instalar Elasticsearch 7.x MCP Server para Claude Desktop automáticamente a través de Smithery :

npx -y @smithery/cli install @imlewc/elasticsearch7-mcp-server --client claude

Instalación manual

pip install -e .

Variables de entorno

El servidor requiere las siguientes variables de entorno:

  • ELASTIC_HOST : Dirección de host de Elasticsearch (por ejemplo, http://localhost:9200 )

  • ELASTIC_USERNAME : nombre de usuario de Elasticsearch

  • ELASTIC_PASSWORD : Contraseña de Elasticsearch

  • MCP_PORT : (opcional) Puerto de escucha del servidor MCP, predeterminado 9999

Uso de Docker Compose

  1. Cree un archivo .env y configure ELASTIC_PASSWORD :

ELASTIC_PASSWORD=your_secure_password
  1. Iniciar los servicios:

docker-compose up -d

Esto iniciará un clúster Elasticsearch 7.17.10 de tres nodos, Kibana y el servidor MCP.

Uso de un cliente MCP

Puede utilizar cualquier cliente MCP para conectarse al servidor MCP:

from mcp import MCPClient

client = MCPClient("localhost:9999")
response = client.call("es-ping")
print(response)  # {"success": true}

Documentación de la API

Métodos MCP admitidos actualmente:

  • es-ping : comprobar la conexión de Elasticsearch

  • es-info : Obtener información del clúster de Elasticsearch

  • es-search : Buscar documentos en el índice de Elasticsearch

Ejemplos de API de búsqueda

Búsqueda básica

# Basic search
search_response = client.call("es-search", {
    "index": "my_index",
    "query": {
        "match": {
            "title": "search keywords"
        }
    },
    "size": 10,
    "from": 0
})

Consulta de agregación

# Aggregation query
agg_response = client.call("es-search", {
    "index": "my_index",
    "size": 0,  # Only need aggregation results, no documents
    "aggs": {
        "categories": {
            "terms": {
                "field": "category.keyword",
                "size": 10
            }
        },
        "avg_price": {
            "avg": {
                "field": "price"
            }
        }
    }
})

Búsqueda avanzada

# Advanced search with highlighting, sorting, and filtering
advanced_response = client.call("es-search", {
    "index": "my_index",
    "query": {
        "bool": {
            "must": [
                {"match": {"content": "search term"}}
            ],
            "filter": [
                {"range": {"price": {"gte": 100, "lte": 200}}}
            ]
        }
    },
    "sort": [
        {"date": {"order": "desc"}},
        "_score"
    ],
    "highlight": {
        "fields": {
            "content": {}
        }
    },
    "_source": ["title", "date", "price"]
})

Desarrollo

  1. Clonar el repositorio

  2. Instalar dependencias de desarrollo

  3. Ejecute el servidor: elasticsearch7-mcp-server

Licencia

[Licencia en archivo LICENSE]

Lengua china

Available Tools

3 tools
es-infoC

Get Elasticsearch info

Inputs: req (required).

es-pingC

Ping Elasticsearch server

Inputs: req (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    C2.6/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: es-info retrieves server information, es-ping checks connectivity, and es-search performs document searches. There is no overlap or ambiguity between these functions, making tool selection straightforward for an agent.

    Naming Consistency5/5

    All tool names follow a consistent 'es-' prefix and underscore-separated verb pattern (es-info, es-ping, es-search). This predictable naming convention enhances readability and usability across the tool set.

    Tool Count2/5

    With only 3 tools, the server feels thin for an Elasticsearch domain, which typically involves operations like indexing, updating, deleting, and aggregating documents. The count is too low to cover the expected scope of a database/search engine server.

    Completeness2/5

    The tool set is severely incomplete for Elasticsearch functionality. It lacks essential CRUD operations (e.g., create, update, delete documents), index management, and query features beyond basic search, which will likely cause agent failures in handling typical database tasks.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      A
      maintenance
      Facilitates interaction with Elasticsearch clusters by allowing users to perform index operations, document searches, and cluster management via a Model Context Protocol server and natural language commands.
      20
      317
      Apache 2.0
    • A
      license
      B
      quality
      D
      maintenance
      An MCP server that enables interaction with Elasticsearch and OpenSearch clusters for searching documents and managing indices. It provides tools for cluster health monitoring, index configuration, and general API requests.
      16
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables secure and efficient interaction with Elasticsearch clusters through the Model Context Protocol, providing tools for data management, search, and export.
      3,584 npm
      1
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables read-only interaction with Elasticsearch, supporting listing indices, retrieving mappings, and executing search/aggregation queries via MCP.
      -