Dremio MCP Server
Dremio data access and query integration via the Model Context Protocol.
Data last scanned today · Reviewed today
Overview
This server bridges Dremio with AI assistants using the Model Context Protocol. It facilitates interaction with Dremio engines, enabling users to leverage Dremio's data querying capabilities directly within LLM-powered environments.
Our verdict
This server carries a high risk level with a security score of 40/100. It is a community-maintained project rather than an official Dremio vendor release, and critical aspects such as the authentication method and read-only mode support have not yet been editorially reviewed. It is suitable for experimental use by developers familiar with the repository, but should be treated with caution in sensitive environments.
- Supports OAuth and external token providers for authentication
- Zero direct dependencies minimize supply-chain surface area
- Includes Helm chart documentation for Kubernetes deployments
- Integrates Prometheus metrics for monitoring
- Not maintained by the official Dremio organization
- Lack of editorial review on critical security components
- No verified status for read-only filesystem implementation
Tools
| Tool | Description | Risk |
|---|---|---|
| GetFailedJobDetails | Analyzes failed/canceled jobs over the past 7 days | low |
| BuildUsageReport | Generates usage reports grouped by engines or projects | low |
| GetRelevantMetrics | Retrieves Prometheus metrics for the Dremio cluster | low |
| RunSqlQuery | Executes SELECT queries on the Dremio cluster | low |
| GetSchemaOfTable | Retrieves schema information for tables | low |
| GetTableOrViewLineage | Finds lineage of tables/views | low |
| SemanticSearch | Performs semantic search across the cluster | low |
| GetNameOfJobsRecentTable | Returns the system table name for job information | low |
| GetUsefulSystemTableNames | Lists important system tables | low |
| GetMetricSchema | Returns metric labels and sample values | low |
Compatibility
| Client | Local | Docker | Remote | Read-only |
|---|---|---|---|---|
| Claude Desktop | ||||
| Cursor | ||||
| VS Code | ||||
| Windsurf | ||||
| ChatGPT |
Frequently asked questions
›What are the software requirements for running the Dremio MCP server locally?
You need Python 3.11 or later and the uv package manager installed.
›How is authentication handled for production deployments?
Production deployments using Helm support OAuth and an external token provider, which is the recommended security configuration.
›Can I use a Personal Access Token (PAT) for production?
No, using a Personal Access Token (PAT) is intended only for development and testing, not for production environments.
›What information is needed to create the Dremio configuration file?
You will need your Dremio URI, a Personal Access Token (PAT), and your project ID if you are using Dremio Cloud.
›What is the recommended approach for deploying the server in Kubernetes?
For production Kubernetes environments, the server should be deployed using the provided Helm chart.
Alternatives
Badge
Maintain this server? Add the live badge to your README.