Skip to main content
Glama
deenesjakoruzh
Aiven-Open

Aiven MCP Server

Official
by Aiven-Open
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

Servidor MCP de Aiven

Un servidor de Protocolo de Contexto Modelo (MCP) para Aiven.

Esto proporciona acceso a los servicios Aiven para PostgreSQL, Kafka, ClickHouse, Valkey y OpenSearch que se ejecutan en Aiven, así como a su ecosistema más amplio de conectores nativos. Esto permite a los LLM crear soluciones integrales para todos los casos de uso.

Características

Herramientas

  • list_projects

    • Enumere todos los proyectos en su cuenta de Aiven.

  • list_services

    • Enumere todos los servicios en un proyecto específico de Aiven.

  • get_service_details

    • Obtenga el detalle de su servicio en un proyecto específico de Aiven.

Related MCP server: MCP TapData Server

Configuración para Claude Desktop

  1. Abra el archivo de configuración de Claude Desktop ubicado en:

    • En macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

    • En Windows: %APPDATA%/Claude/claude_desktop_config.json

  2. Añade lo siguiente:

{
  "mcpServers": {
    "mcp-aiven": {
      "command": "uv",
      "args": [
        "--directory",
        "$REPOSITORY_DIRECTORY",
        "run",
        "--with-editable",
        "$REPOSITORY_DIRECTORY",
        "--python",
        "3.13",
        "mcp-aiven"
      ],
      "env": {
        "AIVEN_BASE_URL": "https://api.aiven.io",
        "AIVEN_TOKEN": "$AIVEN_TOKEN"
      }
    }
  }
}

Actualizar las variables de entorno:

  1. Localice la entrada de comando para uv y reemplácela con la ruta absoluta del ejecutable uv . Esto garantiza que se use la versión correcta de uv al iniciar el servidor. En una Mac, puede encontrar esta ruta usando which uv .

  2. Reinicie Claude Desktop para aplicar los cambios.

Configuración del cursor

  1. Vaya a Cursor -> Configuración -> Configuración del cursor

  2. Seleccione "Servidores MCP"

  3. Agregar un nuevo servidor con

    • Nombre: mcp-aiven

    • Tipo: command

    • Comando: uv --directory $REPOSITORY_DIRECTORY run --with-editable $REPOSITORY_DIRECTORY --python 3.13 mcp-aiven

Donde $REPOSITORY_DIRECTORY es la ruta al repositorio. Es posible que deba agregar las variables AIVEN_BASE_URL , AIVEN_PROJECT_NAME y AIVEN_TOKEN

Desarrollo

  1. Agregue las siguientes variables a un archivo .env en la raíz del repositorio.

AIVEN_BASE_URL=https://api.aiven.io
AIVEN_TOKEN=$AIVEN_TOKEN

  1. Ejecute uv sync para instalar las dependencias. Para instalar uv , siga las instrucciones aquí . Luego, ejecute source .venv/bin/activate .

  2. Para realizar pruebas fácilmente, puede ejecutar mcp dev mcp_aiven/mcp_server.py para iniciar el servidor MCP.

Variables de entorno

Las siguientes variables de entorno se utilizan para configurar la conexión de Aiven:

Variables requeridas

  • AIVEN_BASE_URL : La URL de la API de Aiven

  • AIVEN_TOKEN : El token de autenticación

Consideraciones para desarrolladores sobre protocolos de contexto de modelo (MCP) y agentes de IA

Esta sección describe las responsabilidades clave del desarrollador y las consideraciones de seguridad al trabajar con Protocolos de Contexto de Modelo (MCP) y Agentes de IA en este sistema. MCP autogestionados:

  • Responsabilidad del cliente: Los MCP se ejecutan en el entorno del usuario, no en Aiven. Por lo tanto, los usuarios son los únicos responsables de su gestión operativa, seguridad y cumplimiento normativo, de acuerdo con el modelo de responsabilidad compartida. ( https://aiven.io/responsibility-matrix )

  • Implementación y mantenimiento: los desarrolladores deben gestionar todos los aspectos de la implementación, las actualizaciones y el mantenimiento de MCP.

Seguridad del agente de IA:

  • Control de permisos: El acceso y las capacidades de los agentes de IA se rigen estrictamente por los permisos otorgados al token de API utilizado para su autenticación. Los desarrolladores deben gestionar estos permisos meticulosamente.

  • Manejo de credenciales: Tenga muy en cuenta que los agentes de IA pueden requerir credenciales de acceso (por ejemplo, cadenas de conexión a bases de datos o tokens de servicios de streaming) para realizar acciones en su nombre. Tenga mucho cuidado al proporcionar dichas credenciales a los agentes de IA.

  • Evaluación de riesgos: respete las políticas de seguridad de su organización y realice evaluaciones de riesgos exhaustivas antes de otorgar a los agentes de IA acceso a recursos confidenciales.

Mejores prácticas para tokens API:

  • Principio de Mínimo Privilegio: Adhiérase siempre al principio de mínimo privilegio. Los tokens de API deben tener el alcance y la restricción mínimos necesarios para su función prevista.

  • Gestión de tokens: Implemente prácticas sólidas de gestión de tokens, incluida la rotación regular y el almacenamiento seguro.

Conclusiones clave:

  • Los usuarios conservan el control y la responsabilidad total de la ejecución y la seguridad de MCP.

  • Los permisos del agente de IA están directamente vinculados a los permisos del token API.

  • Tenga mucho cuidado al proporcionar credenciales a los agentes de IA.

  • Adhiérase estrictamente al principio del mínimo privilegio al administrar tokens API.

Available Tools

3 tools
get_service_detailsD
ParametersJSON Schema
NameRequiredDescriptionDefault
project_nameYes
service_nameYes

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.

list_projectsD
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.

list_servicesD
ParametersJSON Schema
NameRequiredDescriptionDefault
project_nameYes

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. Dates show when Glama detected each change.

  1. 3 tool updatesv1.0.0
    • First observedget_service_details
    • First observedlist_projects
    • First observedlist_services
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

D1.8/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: get_service_details retrieves specific service information, list_projects enumerates projects, and list_services enumerates services. There is no overlap in functionality, making tool selection straightforward for an agent.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern (get_service_details, list_projects, list_services) with clear, descriptive names. The naming convention is uniform throughout the set.

Tool Count2/5

With only 3 tools, the server feels under-scoped for managing Aiven services, which typically involve operations like create, update, delete, or configure services. The count is too low for comprehensive coverage of the domain.

Completeness2/5

The tool set is severely incomplete for a service management domain; it lacks essential CRUD operations (e.g., create_service, update_service, delete_service) and other key actions like managing configurations or monitoring, leaving significant gaps that will hinder agent workflows.

Maintenance

ActivityActive
ResponsivenessUnresponsive

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

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

Related MCP Connectors

Related MCP Servers

  • ClickHouse MCP Server

    ThomAub
    A
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server that enables Large Language Models to seamlessly interact with ClickHouse databases, supporting resource listing, schema retrieval, and query execution.
    2
    MIT
  • MCP TapData Server by tapdata

    MCP TapData Serverofficial

    tapdata
    F
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server that enables Large Language Models to access and interact with database connections, including viewing schemas and performing CRUD operations on connected databases.
    -

  • RL-MCP

    rlefko
    F
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server that provides AI models with structured access to external data and services, acting as a bridge between AI assistants and applications, databases, and APIs in a standardized, secure way.
    2
    -

Appeared in Searches

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/Aiven-Open/mcp-aiven'

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