---
title: "AWS Neptune MCP: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/mcp-servers/awslabs-neptune/
description: "Inspect graph schema and execute openCypher or Gremlin against a selected Neptune graph."
---

# AWS Neptune MCP: review, setup & limitations · Undominated.ai

> Inspect graph schema and execute openCypher or Gremlin against a selected Neptune graph.

[← Explore all mcp servers](/mcp-servers/)

AWS DATA SERVICES / AWS Labs

# AWS Neptune MCP

Inspect graph schema and execute openCypher or Gremlin against a selected Neptune graph.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/awslabs/mcp)

SOURCE REVIEW

 Reviewed 2026-10-14
 Evidence 5 linked sources
 Publisher AWS Labs
 Licence [Apache-2.0 ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE)
 Revision 8840003820a7
 [Read what was—and wasn’t—checked ↓](#review)

“Amazon Neptune MCP server for graph status, schema and queries.”

 [AWS Labs · upstream description ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/amazon-neptune-mcp-server/README.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - Specialized publisher integration with documented IAM and data access boundaries.
- Explore graph labels and relationships before writing a bounded openCypher query.
- The README fetches Neptune status and schema and runs openCypher or Gremlin against a configured endpoint.
- It does not filter queries to read-only, so the IAM data-plane permissions are the control the file names.

### A good fit for

 - Explore graph labels and relationships before writing a bounded openCypher query.
- Investigate connected entities in a development Neptune Database or Analytics graph.
- Running openCypher or Gremlin against a Neptune endpoint the process can already reach
- Not as a read-only graph client, because the README says any query is executed

### Weigh up before choosing

 - The server accepts mutating queries as well as reads. No read-only server flag is documented; use IAM data-plane permissions to restrict mutations.
- Neptune Database requires reachability into its private VPC. Analytics may use a configured public endpoint or require private network access.
- Neptune Database supports openCypher and Gremlin; Neptune Analytics supports openCypher. A tool name does not establish that every backend accepts that language.
- Use the documented neptune-db:// or neptune-graph:// endpoint format; generic HTTPS examples in install links do not explain the backend selector.
- The monorepo now recommends Agent Toolkit for AWS for production. This specialized local server remains documented; its leaf and root documentation were checked for deprecation.
- The server does not reject mutating queries. The README says it will run any query sent to it.
- Neptune Database is in a private VPC. The process must be able to reach that network. Analytics may be public only if a public endpoint was configured.
- The README does not add a second confirmation flag for writes.
- A pin does not verify transitive dependencies. Documented uvx examples use a floating package tag, not the reviewed commit.
- This review did not execute the resource.
- The server was not started and its tools were not called.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - src/amazon-neptune-mcp-server/README.md
- src/amazon-neptune-mcp-server/pyproject.toml
- src/amazon-neptune-mcp-server/awslabs/amazon_neptune_mcp_server/server.py
- Root README.md and LICENSE
- LICENSE

### Our findings

 - The pinned entrypoint forwards query strings to backend query methods without establishing a read-only gate.
- README and package metadata establish Python >=3.10, VPC requirements and the two endpoint schemes.
- The server returns graph status and schema and runs openCypher and Gremlin on Neptune Database, and openCypher on Neptune Analytics.
- It needs an AWS profile that can access Neptune, and the host must reach the endpoint. Neptune Database requires access into its private VPC.
- The README says the server will run any query, including mutating ones. It does not implement a read-only mode. Data-plane permissions on the role are the control it points to.

### Not established by this review

 - Server startup, authentication, live tool execution and security isolation were not tested.
- Published package/container parity with a source revision and hosted implementation internals were not tested.
- The server was not started and its tools were not called.
- A pin does not verify transitive dependencies.
- No tools/list or tool call was made.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Connect a server deliberately.

[Upstream setup instructions ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/amazon-neptune-mcp-server/README.md)

DOCUMENTED COMMAND

 uvx awslabs.amazon-neptune-mcp-server@latest Copy command ↗

Copying does not execute this command. It may retrieve a newer version than the reviewed source.

 - Configure a dedicated AWS profile and read-only graph data permissions, plus network access to the target.
- Set NEPTUNE_ENDPOINT to neptune-db://<cluster endpoint> or neptune-graph://<graph identifier>.
- Start the uvx process and inspect status/schema before requesting a bounded query.

### Before you start

 - Python 3.10 or newer, uv/uvx and an MCP client that can launch a local stdio process.
- An AWS account, configured credentials and access to the intended region and service resources.

### Documented configuration example

Use the client and authentication context described in the setup guidance. Configuration formats vary between hosts.

 {
 "mcpServers": {
 "awslabs-neptune": {
 "command": "uvx",
 "args": [
 "awslabs.amazon-neptune-mcp-server@latest"
 ],
 "env": {
 "AWS_PROFILE": "neptune-reader",
 "AWS_REGION": "us-east-1",
 "NEPTUNE_ENDPOINT": "neptune-db://YOUR_CLUSTER_ENDPOINT",
 "FASTMCP_LOG_LEVEL": "ERROR"
 }
 }
 }
} Copy configuration ↗

### Compatibility

Python 3.10 or newer, uv/uvx and an MCP client that can launch a local stdio process. · An AWS account, configured credentials and access to the intended region and service resources.

### Implementation

Python

### Transports

stdio

### AWS data services

 - Returns graph schema and status and forwards openCypher/Gremlin query text to the configured backend.
- Mutation authority follows AWS/data-plane permissions; prompts describing read-only intent are not an access control.

### Cost model

AWS service, model, query and storage charges apply; running the MCP process does not include those services.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Publisher setup, capabilities and operating boundaries ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/amazon-neptune-mcp-server/README.md) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/amazon-neptune-mcp-server/README.md Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports
- [Pinned package and implementation ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/amazon-neptune-mcp-server/pyproject.toml) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/amazon-neptune-mcp-server/pyproject.toml Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports
- [Pinned package and implementation ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/amazon-neptune-mcp-server/awslabs/amazon_neptune_mcp_server/server.py) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/amazon-neptune-mcp-server/awslabs/amazon_neptune_mcp_server/server.py Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports
- [Pinned package and implementation ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/README.md) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/README.md Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports
- [Applicable licence ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE Supports: license

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### AWS Keyspaces MCP ↗ Inspect Cassandra-compatible schemas and run SELECT queries with dedicated database credentials.](/mcp-servers/awslabs-keyspaces/)[### AWS Labs Amazon Kendra Index ↗ Queries an existing Kendra index and returns document excerpts, source URIs and confidence labels for retrieval workflows.](/mcp-servers/awslabs-kendra-index/)[### AWS Labs Amazon MQ ↗ Inspects and manages Amazon MQ brokers, with additional RabbitMQ management operations.](/mcp-servers/awslabs-amazon-mq/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Inspect resource evidence](/tools/)
- [Choose a host](/agents/)
- [Inspect reusable workflows](/skills/)
- [Use Undominated data](/api/)
