Pinot MCP Server
@startreedata
About Pinot MCP Server
MCP Server for Apache Pinot
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-pinot": {
"command": "uv",
"args": [
"pip",
"install",
"-e",
".",
"#",
"Install",
"dependencies"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Pinot MCP Server?
A Python-based MCP server for interacting with Apache Pinot, built using the FastMCP framework. It integrates with Claude Desktop to enable real-time analytics and metadata queries on a Pinot cluster, allowing users to list tables, segments, schema info, execute read-only SQL queries, and view index/column-level metadata.
How to use Pinot MCP Server?
Clone the repository, install dependencies with uv, configure a .env file for the Pinot cluster connection, then run the server. It supports stdio transport for Claude Desktop and HTTP transport for other clients with optional OAuth authentication.
Key features of Pinot MCP Server
- List tables, segments, and schema info from Pinot
- Execute read-only SQL queries with automatic validation
- View index and column-level metadata
- Optional table filtering with glob patterns
- Multiple transport modes (stdio, HTTP, HTTPS with OAuth)
- Read-only query enforcement (SELECT/WITH only)
Use cases of Pinot MCP Server
- Business users analyzing Pinot data through Claude Desktop
- Real-time analytics and metadata queries on Pinot clusters
- Multi-tenant environments with table filtering per team
- Environment-specific deployments (dev, staging, prod) showing relevant tables only
FAQ from Pinot MCP Server
What is the difference between Pinot MCP Server and directly querying Pinot?
It provides an MCP interface for Claude Desktop and other MCP clients, with read-only enforcement, table filtering, and metadata discovery tools that abstract away direct Pinot API calls.
What are the runtime requirements?
Python, the uv package manager, and access to a running Pinot cluster with controller and broker endpoints.
Does Pinot MCP Server support authentication?
Yes. It supports basic authentication via PINOT_USERNAME/PINOT_PASSWORD, token-based auth via PINOT_TOKEN or PINOT_TOKEN_FILENAME, and OAuth for the MCP server endpoint when exposing it remotely.
How does table filtering work?
Table filtering uses a YAML file with glob patterns to limit which tables are visible across all MCP operations. It is a convenience feature for organizing tables, not a security boundary.
Can I use Pinot MCP Server over HTTP or HTTPS?
Yes, set MCP_TRANSPORT=http. For remote access (non-loopback host) you must enable OAuth; TLS can be configured via MCP_SSL_KEYFILE and MCP_SSL_CERTFILE.
More Other MCP servers
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
Inbox Zero AI
elie222The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
🚀 Model Context Protocol (MCP) Curriculum for Beginners
microsoftThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
Peekaboo MCP – lightning-fast macOS screenshots for AI agents
steipetePeekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
Blender
ahujasidOpen-source MCP to use Blender with any LLM
Comments