Skip to main content
Glama
enesjakozh
da-okazaki

MCP Neo4j Server

by da-okazaki
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Servidor MCP Neo4j

insignia de herrería

Un servidor MCP que proporciona integración entre la base de datos de gráficos Neo4j y Claude Desktop, lo que permite operaciones de base de datos de gráficos a través de interacciones de lenguaje natural.

Inicio rápido

Puede ejecutar este servidor MCP directamente usando npx:

npx @alanse/mcp-neo4j

O agréguelo a su configuración de Claude Desktop:

{
  "mcpServers": {
    "neo4j": {
      "command": "npx",
      "args": ["@alanse/mcp-neo4j-server"],
      "env": {
        "NEO4J_URI": "bolt://localhost:7687",
        "NEO4J_USERNAME": "neo4j",
        "NEO4J_PASSWORD": "your-password"
      }
    }
  }
}

Related MCP server: Notion MCP Server

Características

Este servidor proporciona herramientas para interactuar con una base de datos Neo4j:

Herramientas

  • execute_query : Ejecuta consultas Cypher en la base de datos Neo4j

    • Admite todos los tipos de consultas Cypher (LECTURA, CREAR, ACTUALIZAR, ELIMINAR)

    • Devuelve los resultados de la consulta en un formato estructurado

    • Se pueden pasar parámetros para evitar ataques de inyección.

  • create_node : Crea un nuevo nodo en la base de datos del gráfico

    • Especificar etiquetas y propiedades de nodos

    • Devuelve el nodo creado con su ID interno

    • Admite todos los tipos de datos Neo4j para propiedades

  • create_relationship : Crea una relación entre dos nodos existentes

    • Definir el tipo y la dirección de la relación

    • Agregar propiedades a las relaciones

    • Requiere identificadores de nodo para los nodos de origen y destino

Instalación

Instalación mediante herrería

Para instalar MCP Neo4j Server para Claude Desktop automáticamente a través de Smithery :

npx -y @smithery/cli install @alanse/mcp-neo4j-server --client claude

Para el desarrollo

  1. Clonar el repositorio:

git clone https://github.com/da-okazaki/mcp-neo4j-server.git
cd mcp-neo4j-server

  1. Instalar dependencias:

npm install

  1. Construir el proyecto:

npm run build

Configuración

El servidor requiere las siguientes variables de entorno:

  • NEO4J_URI : URI de la base de datos Neo4j (predeterminado: bolt://localhost:7687)

  • NEO4J_USERNAME : nombre de usuario de Neo4j (predeterminado: neo4j)

  • NEO4J_PASSWORD : Contraseña de Neo4j (obligatoria)

Ejemplos de uso

A continuación se muestran ejemplos de cómo puedes interactuar con la base de datos Neo4j utilizando lenguaje natural:

Consulta de datos

Puedes hacer preguntas como:

  • "Muéstrame todos los empleados del departamento de Ventas"

  • Encuentra a los 5 clientes más antiguos

  • ¿Quién ha comprado más de 3 productos en el último mes?

Ejemplo:

User: "Show me all employees in the Sales department"

Claude: Let me query the database for Sales department employees.

[Executes query internally: MATCH (e:Employee)-[:WORKS_IN]->(d:Department {name: 'Sales'}) RETURN e.name, e.position]

Result:
- John Smith (Sales Manager)
- Sarah Johnson (Sales Representative)
- Mike Brown (Account Executive)

Creando datos

Puedes dar instrucciones como:

  • "Agregar una nueva persona llamada John Doe que tenga 30 años"

  • Crear un producto llamado 'Café Premium' con un precio de $24.99.

  • "Añadir un nuevo departamento llamado 'Investigación y Desarrollo'"

Ejemplo:

User: "Add a new person named John Doe who is 30 years old"

Claude: I'll create a new Person node with the provided information.

[Creates node internally with label 'Person' and properties {name: 'John Doe', age: 30}]

Result: Created new person node with ID: 123

Creando relaciones

Puedes solicitar relaciones como:

  • "Haz que John Doe se haga amigo de Jane Smith"

  • "Establecer el Producto A como componente del Producto B"

  • "Asignar a John Doe al departamento de Ventas"

Ejemplo:

User: "Make John Doe friends with Jane Smith"

Claude: I'll create a friendship relationship between these two people.

[Creates relationship internally: MATCH (a:Person {name: 'John Doe'}), (b:Person {name: 'Jane Smith'})
CREATE (a)-[:FRIENDS_WITH {since: '2024-01-05'}]->(b)]

Result: Created friendship relationship between John Doe and Jane Smith

Operaciones complejas

Puedes realizar operaciones más complejas con lenguaje natural:

  • Encuentra todos los productos adquiridos por clientes que viven en Nueva York.

  • "Muéstrame los amigos de los amigos de John Doe"

  • Calcular la edad media de los empleados de cada departamento.

Ejemplo:

User: "Find all products purchased by customers who live in New York"

Claude: I'll query the database for this information.

[Executes query internally:
MATCH (c:Customer {city: 'New York'})-[:PURCHASED]->(p:Product)
RETURN c.name, collect(p.name) as products]

Result:
- Alice Wilson: [Premium Coffee, Tea Set, Cookies]
- Bob Miller: [Premium Coffee, Water Bottle]

Pruebas

Ejecute el conjunto de pruebas:

npm test

Licencia

Instituto Tecnológico de Massachusetts (MIT)

Available Tools

3 tools
create_nodeB

Create a new node in Neo4j

ParametersJSON Schema
NameRequiredDescriptionDefault
labelYesNode label
propertiesYesNode properties

TDQS

B3.1/5.0
Behavior2/5

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

No annotations exist, so description must disclose behavioral traits; but it only states the action without mentioning side effects, permissions, constraints, or return value.

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

Conciseness4/5

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

Single sentence is concise and front-loaded, but more context could be added without sacrificing brevity.

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 (2 params, no output schema, no annotations), the description is too minimal; it lacks details on behavior, error handling, and return values.

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 coverage is 100% with descriptions for 'label' and 'properties'; the description adds no extra meaning beyond the schema.

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

Purpose5/5

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

The description 'Create a new node in Neo4j' uses a specific verb and resource, clearly distinguishing it from sibling tools like create_relationship and execute_query.

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?

No guidance on when to use this tool versus alternatives, no when-not-to-use or prerequisites provided.

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

create_relationshipB

Create a relationship between two nodes

ParametersJSON Schema
NameRequiredDescriptionDefault
typeYesRelationship type
toNodeIdYesID of the target node
fromNodeIdYesID of the source node
propertiesNoRelationship properties

TDQS

B3.1/5.0
Behavior2/5

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

No annotations provided, so description must disclose behavior. It only states the action without revealing constraints, failure conditions, or required privileges.

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

Conciseness4/5

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

Single sentence is very concise, but lacks necessary detail. However, it is not verbose, so it earns a high score for conciseness.

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 4 parameters including a nested object and no output schema, the description is too brief. It should explain directionality, required type, and optional properties.

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 covers 100% of parameters, so baseline is 3. Description adds no additional meaning beyond the schema, such as explaining relationship direction or properties usage.

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

Purpose5/5

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

Description clearly states verb 'Create' and resource 'relationship between two nodes', which is specific and distinct from sibling tools that create nodes or execute queries.

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?

No guidance on when to use this tool vs alternatives like execute_query for creating relationships. No mention of prerequisites or when not to use it.

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

execute_queryC

Execute a Cypher query on Neo4j database

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesCypher query to execute
paramsNoQuery parameters

TDQS

C2.7/5.0
Behavior1/5

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

With no annotations, the description must disclose behavioral traits but fails to do so. It omits information about side effects (e.g., mutation vs read), error behavior, or required permissions.

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

Conciseness4/5

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

The description is a single, clear sentence with no extraneous words. It is efficient but could be slightly expanded without losing conciseness.

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 lack of output schema and annotations, the description is incomplete. It does not explain return values, error handling, or important behavioral context for a general query executor.

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 baseline is 3. The description adds no extra meaning beyond the schema's parameter descriptions.

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 verb 'Execute' and the resource 'a Cypher query on Neo4j database'. It distinguishes from sibling tools (create_node, create_relationship) by indicating general query execution rather than specific node/relationship creation.

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?

No guidance is provided on when to use this tool versus the siblings. The description does not mention context or exclusions, leaving the agent without direction for tool selection.

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. 3 tool updatesv1.0.1
    • First observedcreate_node
    • First observedcreate_relationship
    • First observedexecute_query
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

B3.3/5.0

Scored across 3 tools

Disambiguation5/5

Each tool targets a distinct operation: creating nodes, creating relationships, and executing arbitrary queries. There is no overlap.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern in snake_case: create_node, create_relationship, execute_query.

Tool Count4/5

With 3 tools, the server is slightly small but still reasonable for a focused database interface. The tools cover essential create and query operations.

Completeness3/5

The server lacks direct update and delete operations on nodes/relationships. While execute_query can handle these via Cypher, it creates a dependency on raw queries, which is a notable gap.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

  • MCP-Python

    rhabraken
    F
    license
    Not graded
    quality
    D
    maintenance
    A server that enables interaction with PostgreSQL, MySQL, MariaDB, or SQLite databases through Claude Desktop using natural language queries.
    1
    -
  • Kuzu MCP server by kuzudb

    Kuzu MCP serverofficial

    kuzudb
    A
    license
    B
    quality
    F
    maintenance
    This server enables natural language interaction between a user and their Kuzu databases using clients like Claude Desktop or Cursor, allowing LLMs to retrieve the database schema, execute Cypher queries, create nodes, and establish relationships in the graph database.
    2
    42
    MIT

Appeared in Searches