Dgraph MCP Server

🚀 Dgraph MCP Server

A Model Context Protocol (MCP) server for Dgraph graph database implemented using the mcp-go library.

🚀 Quick Start

This project implements an MCP server that interacts with the Dgraph database, allowing Large Language Model (LLM) applications to perform the following operations:

• Execute DQL queries
• Perform mutation operations
• Modify the schema
• Retrieve the current schema

✨ Features

• Enables seamless interaction between LLM applications and Dgraph databases.
• Supports multiple operations such as querying, mutating, and schema modification.
• Communicates with LLM applications via standard input/output.

📦 Installation

Prerequisites

• Go 1.18 or higher
• A running Dgraph database (local or remote)

Steps

1. Clone this repository.
2. Install dependencies:

go mod download

📚 Documentation

Configuration

The server can be configured using environment variables:

• DGRAPH_HOST: The address of the Dgraph service (default: localhost:9080)

Usage

Run the Server

go run main.go

The server communicates with LLM applications using standard input/output.

Available Tools

1. dgraph_query

Execute a DQL query on Dgraph.

• Parameters:
  • query (string, required): The DQL query to execute.
  • variables (object, optional): Variables in the query.
• Example:

{
  "tool": "dgraph_query",
  "params": {
    "query": "{ me(func: has(name)) { name } }"
  }
}

2. dgraph_mutate

Perform a mutation operation on Dgraph.

• Parameters:
  • mutation (string, required): The RDF mutation to execute.
  • commit (boolean, optional): Whether to commit the transaction (default: true).
• Example:

{
  "tool": "dgraph_mutate",
  "params": {
    "mutation": "_:person <name> \"John Doe\" .",
    "commit": true
  }
}

3. dgraph_alter_schema

Modify the Dgraph schema.

• Parameters:
  • schema (string, required): The schema definition to apply.
• Example:

{
  "tool": "dgraph_alter_schema",
  "params": {
    "schema": "name: string @index(exact) ."
  }
}

Available Resources

1. dgraph://schema

Returns the current Dgraph schema.

Integration with LLM Applications

This server can be integrated with any LLM framework that supports the MCP protocol. It communicates via standard input/output, making it easy to integrate with various LLM tool frameworks.

💻 Usage Examples

Basic Query

{
  people(func: has(name)) {
    name
    age
    friends {
      name
    }
  }
}

Add Data

_:alice <name> "Alice" .
_:alice <age> "30" .
_:bob <name> "Bob" .
_:bob <age> "32" .
_:alice <friend> _:bob .

Schema Definition

name: string @index(exact) .
age: int .
friend: [uid] .

📄 License

MIT