Skip to main content
Glama
nebula-contrib

NebulaGraph MCP Server

by nebula-contrib
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote
README.md
# Model Context Protocol Server for NebulaGraph


A Model Context Protocol (MCP) server implementation that provides access to [NebulaGraph](https://github.com/vesoft-inc/nebula).

[![PyPI - Version](https://img.shields.io/pypi/v/nebulagraph-mcp-server)](https://pypi.org/project/nebulagraph-mcp-server/)
[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/nebulagraph-mcp-server)](https://pypi.org/project/nebulagraph-mcp-server/)
[![Lint and Test](https://github.com/PsiACE/nebulagraph-mcp-server/actions/workflows/test.yml/badge.svg)](https://github.com/PsiACE/nebulagraph-mcp-server/actions/workflows/test.yml)

## Features

- Seamless access to NebulaGraph 3.x .
- Get ready for graph exploration, you know, Schema, Query, and a few shortcut algorithms.
- Follow Model Context Protocol, ready to integrate with LLM tooling systems.
- Simple command-line interface with support for configuration via environment variables and .env files.

![LlamaIndex with NebulaGraph MCP](./assets/llamaindex-with-nebulagraph-mcp.png)

## Installation

```shell
pip install nebulagraph-mcp-server
```

## Usage

`nebulagraph-mcp-server` will load configs from `.env`, for example:

```
NEBULA_VERSION=v3 # only v3 is supported
NEBULA_HOST=<your-nebulagraph-server-host>
NEBULA_PORT=<your-nebulagraph-server-port>
NEBULA_USER=<your-nebulagraph-server-user>
NEBULA_PASSWORD=<your-nebulagraph-server-password>
```

> It requires the value of `NEBULA_VERSION` to be equal to v3 until we are ready for v5.

## Development

```shell
npx @modelcontextprotocol/inspector \
  uv run nebulagraph-mcp-server
```

## Credits

The layout and workflow of this repo is copied from [mcp-server-opendal](https://github.com/Xuanwo/mcp-server-opendal).
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 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: execute_query for general queries, find_neighbors for vertex adjacency, find_path for pathfinding, get_space_schema for schema inspection, and list_spaces for space enumeration. The descriptions reinforce these distinct functions, making tool selection unambiguous.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (e.g., execute_query, find_neighbors, list_spaces) with clear, descriptive verbs. There are no deviations in style or convention, making the naming predictable and easy to understand across the set.

Tool Count5/5

With 5 tools, this server is well-scoped for graph database operations, covering essential functions like querying, traversal, pathfinding, and schema management. Each tool earns its place without feeling excessive or insufficient for the domain.

Completeness4/5

The tool set provides strong coverage for core graph operations, including query execution, neighbor and path finding, and space/schema inspection. A minor gap exists in CRUD operations for vertices or edges (e.g., create, update, delete), but agents can likely work around this with queries.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources