What NebulaGraph version is supported?
Only NebulaGraph v3 is currently supported. The `NEBULA_VERSION` environment variable must be set to `v3`.
@PsiACE
Basic information
Model Context Protocol Server for NebulaGraph 3.x
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"nebulagraph-mcp-server": {
"command": "npx",
"args": [
"@modelcontextprotocol/inspector",
"\\"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
The Model Context Protocol Server for NebulaGraph is an MCP server that provides LLM tooling systems with seamless access to NebulaGraph 3.x. It enables graph exploration by exposing schema, query capabilities, and shortcut algorithms through the Model Context Protocol.
Install via pip (pip install nebulagraph-mcp-server) and configure using environment variables or a .env file with NEBULA_VERSION, NEBULA_HOST, NEBULA_PORT, NEBULA_USER, and NEBULA_PASSWORD. Then run the command-line tool, which automatically loads the configuration.
.env files.Only NebulaGraph v3 is currently supported. The `NEBULA_VERSION` environment variable must be set to `v3`.
Set environment variables `NEBULA_HOST`, `NEBULA_PORT`, `NEBULA_USER`, `NEBULA_PASSWORD`, and `NEBULA_VERSION` in a `.env` file or in your shell. The server reads these at startup.
No. Only v3 is supported until the project is updated for v5 compatibility.
Install via PyPI with `pip install nebulagraph-mcp-server`.
The Model Context Protocol (MCP) is a standard for integrating tools with LLM systems. This server implements MCP to allow LLMs to interact with NebulaGraph.

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
🚀 The fast, Pythonic way to build MCP servers and clients.
A curated list of references for MLOps
A search tool helps dev to solve the naming things problem.
Hindsight: Agent Memory That Learns
Comments