Skip to main content
Glama
enesjakozh
manpreet2000

MCP Database Server

by manpreet2000
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Servidor de base de datos MCP

Implementación de servidor del Protocolo de Contexto de Modelo (MCP) que permite que los Modelos de Lenguaje Grandes (LLM) interactúen con diversas bases de datos mediante lenguaje natural. Actualmente es compatible con MongoDB y se prevé que también lo sea:

  • PostgreSQL

  • Base de datos de cucarachas

  • Redis

  • Y más...

Características

  • Operaciones de bases de datos mediante lenguaje natural

  • Actualmente es compatible con MongoDB con las siguientes características:

    • Listar todas las colecciones

    • Consultar documentos con filtrado y proyección

    • Insertar documentos

    • Eliminar documentos

    • Operaciones de tuberías de agregados

  • Soporte futuro para otras bases de datos:

    • PostgreSQL: consultas SQL, operaciones de tabla

    • CockroachDB: Operaciones SQL distribuidas

    • Redis: Operaciones clave-valor, almacenamiento en caché

Related MCP server: MongoDB

Prerrequisitos

  • Node.js v20.12.2 o superior

  • Base de datos (actualmente MongoDB, próximamente se añadirán otras bases de datos)

  • Aplicación de escritorio Claude

Instalación

  1. Clonar el repositorio:

git clone https://github.com/manpreet2000/mcp-database-server.git
cd mcp-database-server

  1. Instalar dependencias:

npm install

  1. Construya el código TypeScript:

npm run build

Configuración

Para comenzar, debe configurar su conexión de base de datos en el archivo de configuración de Claude Desktop:

Sistema operativo Mac

~/Library/Application\ Support/Claude/claude_desktop_config.json

Ventanas

%APPDATA%/Claude/claude_desktop_config.json

Agregue la siguiente configuración a su claude_desktop_config.json :

{
  "mcpServers": {
    "database": {
      "command": "/path/to/node",
      "args": ["/path/to/mcp-database/dist/index.js"],
      "env": {
        "MONGODB_URI": "your-mongodb-connection-string"
      }
    }
  }
}

Reemplazar:

  • /path/to/node con su ruta ejecutable Node.js o simplemente use node

  • /path/to/mcp-database con la ruta absoluta a este repositorio

  • your-mongodb-connection-string con la URL de su conexión MongoDB

Ejemplos de uso

Ejemplos de MongoDB

  1. Enumere todas las colecciones en su base de datos:

Can you show me all the collections in my database?

  1. Obtener registros específicos de una colección:

Give me 2 records from the chargers collection

  1. Consulta con filtros:

Show me all documents in the users collection where status is active

  1. Insertar un documento:

Add a new user to the users collection with name John and email john@example.com

  1. Eliminar un documento:

Remove the user with email john@example.com from the users collection

  1. Datos agregados:

Show me the total count of users by status in the users collection

Herramientas disponibles

1. obtener colecciones

Enumera todas las colecciones en la base de datos conectada.

2. obtenerColección

Recupera documentos de una colección con parámetros de consulta opcionales:

  • collectionName : Nombre de la colección

  • limit : Número máximo de documentos a devolver (predeterminado: 10, máximo: 1000)

  • query : objeto de consulta de MongoDB

  • projection : Campos a incluir/excluir

3. insertOne

Inserta un solo documento en una colección:

  • collectionName : Nombre de la colección

  • document : Objeto de documento a insertar

4. deleteOne

Elimina un solo documento de una colección:

  • collectionName : Nombre de la colección

  • query : Consulta para que coincida con el documento a eliminar

5. agregado

Ejecuta una canalización de agregación:

  • collectionName : Nombre de la colección

  • pipeline : Matriz de etapas de agregación

  • options : Opciones de agregación opcionales

Soporte de bases de datos futuras

PostgreSQL

  • Ejecución de consultas SQL

  • Operaciones de tabla

  • Gestión de esquemas

  • Soporte para transacciones

Base de datos de cucarachas

  • Operaciones SQL distribuidas

  • Soporte multirregional

  • Gestión de transacciones

  • Operaciones de esquema

Redis

  • Operaciones clave-valor

  • Mecanismos de almacenamiento en caché

  • Operaciones de pub/suscripción

  • Operaciones de estructura de datos

Seguridad

  • Nunca envíe sus cadenas de conexión de base de datos al control de versiones

  • Utilice variables de entorno para información confidencial

  • Siga las mejores prácticas de seguridad específicas de la base de datos

Contribuyendo

¡Agradecemos sus contribuciones! No dude en enviar una solicitud de incorporación de cambios. Para cambios importantes, primero abra una incidencia para comentar qué desea cambiar.

Licencia

Licencia MIT: consulte LICENCIA para obtener más detalles

Available Tools

5 tools
aggregateD
ParametersJSON Schema
NameRequiredDescriptionDefault
collectionNameYes
pipelineYes
optionsNo

TDQS

D1/5.0
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

deleteOneD
ParametersJSON Schema
NameRequiredDescriptionDefault
collectionNameYes
queryYes

TDQS

D1/5.0
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

getCollectionD
ParametersJSON Schema
NameRequiredDescriptionDefault
collectionNameYes
limitNo
queryNo
projectionNo

TDQS

D1/5.0
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

getCollectionsD
ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

D1/5.0
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

insertOneD
ParametersJSON Schema
NameRequiredDescriptionDefault
collectionNameYes
documentYes

TDQS

D1/5.0
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

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

  1. 5 tool updates
    • First observedaggregate
    • First observeddeleteOne
    • First observedgetCollection
    • First observedgetCollections
    • First observedinsertOne
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

D1.5/5.0

Scored across 5 tools

Disambiguation4/5

The tools have distinct purposes: aggregate, deleteOne, getCollection, getCollections, and insertOne each target different database operations. However, getCollection and getCollections could potentially be confused due to similar naming and lack of descriptions clarifying their exact differences.

Naming Consistency2/5

Naming is inconsistent with mixed conventions: getCollection and getCollections use camelCase, while deleteOne and insertOne use camelCase with different verb styles, and aggregate stands alone. There is no predictable pattern across all tools.

Tool Count3/5

With 5 tools, the count is reasonable for a database server, but it feels borderline thin for covering full CRUD operations and database management. Key operations like update or query filtering are missing, making the set feel incomplete.

Completeness2/5

The tool set has significant gaps for a database server: it lacks update operations, query filtering tools, and transaction management. While basic insert, delete, and get operations are present, the surface is incomplete for typical database workflows, likely causing agent failures.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MongoDB

    QuantGeekDev
    A
    license
    Not graded
    quality
    F
    maintenance
    A Model Context Protocol (MCP) server that enables LLMs to interact directly with MongoDB databases. Query collections, inspect schemas, and manage data seamlessly through natural language.
    28 npm
    175
    MIT

  • MongoDB

    kiliczsh
    A
    license
    B
    quality
    A
    maintenance
    A Model Context Protocol server that provides access to MongoDB databases. This server enables LLMs to inspect collection schemas and execute read-only queries.
    8
    230 npm
    282
    MIT

  • MongoDB MCP Server for LLMs

    nickiiitu
    A
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server that enables LLMs to interact directly with MongoDB databases, allowing users to query collections, inspect schemas, and manage data through natural language.
    28 npm
    2
    MIT

  • MongoDB MCP Server for LLMs

    vivek1612
    A
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server that enables LLMs to interact directly with MongoDB databases, allowing users to query collections, inspect schemas, and manage data through natural language.
    28 npm
    MIT

Appeared in Searches