Skip to main content
Glama
YrsonHTM

MCP Oracle Server

by YrsonHTM
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Remote

MCP Oracle Server

Este proyecto es un servidor Node.js que expone herramientas para interactuar con una base de datos Oracle a través del protocolo Model Context Protocol (MCP). Permite ejecutar consultas SELECT, describir tablas y listar tablas disponibles en la base de datos Oracle de forma segura y controlada.

¿Para qué sirve?

  • Ejecutar consultas SELECT sobre una base de datos Oracle.

  • Describir la estructura de cualquier tabla Oracle.

  • Listar todas las tablas disponibles para el usuario conectado.

  • Facilita la integración de bases de datos Oracle con herramientas que soportan MCP.

Related MCP server: Mini Oracle MCP Server

Requisitos

  • Node.js >= 18

  • Acceso a una base de datos Oracle

  • Tener configuradas las variables de entorno para la conexión Oracle:

    • ORACLE_USER

    • ORACLE_PASSWORD

    • ORACLE_HOST

    • ORACLE_PORT

    • ORACLE_DATABASE

Instalación

  1. Clona el repositorio:

    git clone https://github.com/YrsonHTM/mcp-oracle-server.git
cd mcp-oracle-server

  2. Instala las dependencias:

    npm install

Uso

Iniciar el servidor

npm start

El servidor se ejecutará y estará listo para recibir comandos MCP por stdio.

Herramientas disponibles

  • execute_query: Ejecuta una consulta SELECT en Oracle.

  • describe_table: Describe la estructura de una tabla.

  • list_tables: Lista todas las tablas disponibles para el usuario.

Ejemplo de uso en Cursor

Puedes integrar este servidor con Cursor para interactuar con tu base de datos Oracle desde la propia interfaz de Cursor.

1. Configura el archivo mcp.json

Crea (o edita) el archivo mcp.json en la ruta c:\Users\<TU_USUARIO>\.cursor\mcp.json (en Windows) o ~/.cursor/mcp.json (en Linux/Mac). Ejemplo de configuración:

{
  "mcpServers": {
    "oracle-db": {
      "command": "node",
      "args": ["RUTA_DONDE_INSTALA_EL_SERVER: EJ: C:\\mcp-oracle-server\\server.js"],
      "env": {
        "ORACLE_HOST": "HOST_SERVER: EJ:10.10.10.10",
        "ORACLE_PORT": "PRT: EJ:1521",
        "ORACLE_DATABASE": "NOMBRE_BASE_DATOS: EJ:pruebadb",
        "ORACLE_USER": "NOMBRE_USUARIO: EJ:admin",
        "ORACLE_PASSWORD": "CONTRASEÑAñ EJ:1234"
      }
    }
  }
}

  • Cambia las rutas y credenciales según tu entorno y base de datos.

  • Asegúrate de que la ruta a server.js sea la correcta.

2. Agrega el servidor MCP en Cursor

  • Abre Cursor.

  • Ve a la configuración de MCP (Model Context Protocol).

  • Haz clic en "Agregar servidor MCP" y selecciona el nombre que configuraste (por ejemplo, oracle-db).

  • Inicia el servidor desde Cursor o manualmente con npm start.

3. Usa las herramientas desde Cursor

Ahora puedes ejecutar consultas, describir tablas y listar tablas directamente desde la interfaz de Cursor usando el servidor MCP que configuraste.

Notas

  • El servidor solo permite consultas SELECT para evitar modificaciones accidentales en la base de datos.

  • Si tienes problemas con la conexión Oracle, revisa que las variables de entorno estén correctamente configuradas.

Licencia

MIT

Available Tools

3 tools
describe_tableC

Describe la estructura de una tabla

ParametersJSON Schema
NameRequiredDescriptionDefault
table_nameYesNombre de la tabla a describir

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool describes table structure but doesn't reveal what that entails (e.g., column names, types, constraints), whether it's a read-only operation, potential errors (e.g., if the table doesn't exist), or any permissions required. This leaves significant gaps for a tool that interacts with database metadata.

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

Conciseness5/5

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

The description is a single, efficient sentence in Spanish that directly states the tool's function. It's front-loaded with the core purpose and contains no redundant or unnecessary information, making it highly concise and well-structured.

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

Completeness2/5

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

Given the tool's complexity (interacting with database metadata), lack of annotations, and no output schema, the description is incomplete. It doesn't explain what 'estructura' includes (e.g., schema details), potential outputs, or behavioral aspects like error handling. For a tool with these gaps, more context is needed to be fully helpful.

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

Parameters3/5

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

The schema description coverage is 100%, with the single parameter 'table_name' well-documented in the schema as 'Nombre de la tabla a describir'. The description doesn't add any parameter details beyond what the schema provides, so it meets the baseline of 3 for high schema coverage without compensating value.

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

Purpose4/5

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

The description 'Describe la estructura de una tabla' clearly states the tool's purpose: describing a table's structure. It uses a specific verb ('describe') and resource ('tabla'), but doesn't explicitly differentiate from sibling tools like 'list_tables' or 'execute_query' beyond the structural focus. The Spanish phrasing is clear but lacks sibling distinction.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'list_tables' (which might list table names) or 'execute_query' (which might retrieve data), nor does it specify prerequisites or appropriate contexts for describing table structure versus other operations.

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

execute_queryC

Ejecuta una consulta SELECT en la base de datos Oracle

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesConsulta SQL SELECT a ejecutar

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. While 'execute a SELECT query' implies a read-only operation, it doesn't explicitly state this, nor does it mention potential risks (e.g., performance impact, data exposure), authentication requirements, or result limitations. The description provides minimal behavioral context beyond the basic operation.

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

Conciseness5/5

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

The description is a single, efficient sentence in Spanish that directly states the tool's function without any wasted words. It's appropriately sized and front-loaded with the essential information.

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

Completeness2/5

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

For a database query execution tool with no annotations and no output schema, the description is insufficient. It doesn't explain what the tool returns (result sets, error formats), performance considerations, security constraints, or how it differs from sibling tools. The description leaves critical contextual gaps for proper tool selection and use.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents the single 'query' parameter. The description adds no additional parameter semantics beyond what's in the schema (it just restates that it's a SELECT query). Baseline 3 is appropriate when schema does the heavy lifting.

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

Purpose4/5

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

The description clearly states the action ('execute') and resource ('SELECT query on Oracle database'), providing specific verb+resource information. However, it doesn't explicitly differentiate from sibling tools like 'describe_table' or 'list_tables', which prevents a perfect score.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives like 'describe_table' or 'list_tables'. It doesn't mention prerequisites, limitations, or appropriate contexts for executing SELECT queries versus using the sibling tools.

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

list_tablesB

Lista todas las tablas disponibles para el usuario actual

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.1/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden but only states it lists tables for the current user. It doesn't disclose behavioral traits such as permissions needed, rate limits, pagination, or output format, leaving significant gaps for a tool with zero annotation coverage.

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

Conciseness5/5

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

The description is a single, efficient sentence in Spanish that directly states the tool's purpose without unnecessary words. It is appropriately sized and front-loaded, with no wasted content.

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

Completeness2/5

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

Given the tool's simplicity (0 parameters, no output schema), the description is minimal but incomplete. It lacks details on behavioral aspects like permissions or output structure, which are important even for a simple tool with no annotations, making it inadequate for full context.

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

Parameters4/5

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

The tool has 0 parameters with 100% schema description coverage, so the schema fully documents the lack of inputs. The description adds no parameter information, but this is acceptable given the baseline for zero parameters is 4, as it doesn't need to compensate for missing details.

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

Purpose4/5

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

The description clearly states the action ('Lista todas' - lists all) and resource ('tablas disponibles' - available tables), making the purpose understandable. However, it doesn't differentiate from sibling tools like 'describe_table' or 'execute_query', which prevents a score of 5.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives like 'describe_table' (for table details) or 'execute_query' (for querying data). It lacks context about prerequisites or exclusions, offering only basic functionality.

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 observeddescribe_table
    • First observedexecute_query
    • First observedlist_tables
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.2/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: describe_table for table structure, execute_query for running SELECT queries, and list_tables for enumerating available tables. There is no overlap in functionality, making tool selection straightforward.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (describe_table, execute_query, list_tables) with clear, descriptive verbs and nouns. The naming is uniform and predictable throughout the set.

Tool Count3/5

With only 3 tools, the set feels thin for an Oracle database server, lacking essential operations like INSERT, UPDATE, DELETE, or transaction management. While the tools cover basic query and metadata needs, the count is borderline for a database interface.

Completeness2/5

The toolset is severely incomplete for an Oracle database domain. It only supports SELECT queries and metadata listing, missing critical CRUD operations (create, update, delete), schema modifications, and advanced database management features, leading to significant gaps in agent workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues

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

  • oracle-db-mcp

    Kuass
    A
    license
    Not graded
    quality
    C
    maintenance
    MCP server for accessing Oracle databases, enabling schema exploration, query execution, and performance analysis.
    MIT

  • Oracle Read-Only MCP Server

    pos123
    F
    license
    Not graded
    quality
    C
    maintenance
    A read-only MCP server for Oracle databases that enables SQL queries, schema inspection, and data sampling without requiring OCI client libraries. It supports both TNS alias and direct connection modes with robust security guardrails.
    -

  • Oracle MCP Server

    AlexandruDodita
    F
    license
    Not graded
    quality
    C
    maintenance
    A read-only MCP server for exploring and querying Oracle schemas safely. Provides tools for table listing, schema description, column search, and validated SELECT execution.
    2
    -

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/YrsonHTM/mcp-oracle-server'

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