Atlas / MCP servers / nebula-contrib / NebulaGraph

NebulaGraphSAFE

mcp/nebula-contrib/nebulagraph-1

Model Context Protocol Server for NebulaGraph 3.x

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
5 4r · 1w · 0d
Transport
—
License
Apache-2.0
Stars
29
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

A Model Context Protocol (MCP) server implementation that provides access to NebulaGraph.

[](https://pypi.org/project/nebulagraph-mcp-server/) [](https://pypi.org/project/nebulagraph-mcp-server/) [](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.

Installation

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=
NEBULA_PORT=
NEBULA_USER=
NEBULA_PASSWORD=
It requires the value of NEBULA_VERSION to be equal to v3 until we are ready for v5.

Development

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

Credits

The layout and workflow of this repo is copied from mcp-server-opendal.

Read from source at commit 73ed7af144faOBSERVED · 2026-10-08
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add nebulagraph-mcp-server --env NEBULA_PASSWORD=${NEBULA_PASSWORD} --env OPENAI_API_KEY=${OPENAI_API_KEY} -- uvx nebulagraph-mcp-server
claude-desktop
{
  "mcpServers": {
    "nebulagraph-mcp-server": {
      "command": "uvx",
      "args": [
        "nebulagraph-mcp-server"
      ],
      "env": {
        "NEBULA_PASSWORD": "${NEBULA_PASSWORD}",
        "OPENAI_API_KEY": "${OPENAI_API_KEY}"
      }
    }
  }
}
03

Exposed tools (5)

4 read · 1 write · 0 destructive.

ToolRiskDescription
execute_querywriteExecute a query
find_neighborsreadFind the neighbors of the specified vertex
find_pathreadFind paths between two vertices
get_space_schemareadGet the schema information of the specified space
list_spacesreadList all available spaces
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (2)

LOWPrompt injection · prompt.credential_read · CWE-94, CWE-1427
README.md:27
`nebulagraph-mcp-server` will load configs from `.env`, for example:
Why it matters. asks the agent to read credentials
INFOInventory / provenance · inv.oversize · CWE-1104
assets/llamaindex-with-nebulagraph-mcp.png
assets/llamaindex-with-nebulagraph-mcp.png
Why it matters. 1007759 bytes not read

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 73ed7af144fafull audit observations/trust-audit/mcp-server/nebula-contrib__nebulagraph-1.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-0873ed7af144faSAFEB89first audit
06

Questions

What is the NebulaGraph MCP server?

Model Context Protocol Server for NebulaGraph 3.x

What tools does NebulaGraph expose?

5 in total: 4 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is NebulaGraph safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does NebulaGraph need?

It reads NEBULA_PASSWORD and OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How current is this page?

The grade is for one exact copy of the source (73ed7af144fa), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement