Developer · Local MCP server
Apache Pinot MCP Server
Query and manage Apache Pinot through MCP with typed tools and preview-first safety.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.startreedata/mcp-pinot- Version
- 4.1.0
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- PyPI, OCI image (Docker)
- Published
- 2026-08-29
- Updated
- 2026-08-29
- Publisher
- startreedata (GitHub)
- Website
- startreedata.github.io/mcp-pinot/
- Repository
- github.com/startreedata/mcp-pinot
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPI | mcp-pinot-server | 4.1.0 | stdio |
| OCI image (Docker) | ghcr.io/startreedata/mcp-pinot:4.1.0 | — | stdio |
How to connect Apache Pinot MCP Server
Apache Pinot MCP Server runs locally from a Python package published to PyPI: mcp-pinot-server version 4.1.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx mcp-pinot-server. It reads these environment variables: PINOT_CONTROLLER_URL, PINOT_BROKER_URL, PINOT_USERNAME, PINOT_PASSWORD (secret), PINOT_TOKEN (secret), PINOT_USE_MSQE, MCP_TRANSPORT and AUTH_PROVIDER; set them in the client's configuration for this server.
Apache Pinot MCP Server runs locally from a container image in an OCI registry such as Docker Hub or GitHub Container Registry: ghcr.io/startreedata/mcp-pinot:4.1.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Docker or another OCI container runtime; started with docker run — the usual command is docker run -i --rm ghcr.io/startreedata/mcp-pinot:4.1.0.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"mcp-pinot": {
"command": "uvx",
"args": [
"mcp-pinot-server"
],
"env": {
"PINOT_CONTROLLER_URL": "<value>",
"PINOT_BROKER_URL": "<value>",
"PINOT_USERNAME": "<value>",
"PINOT_PASSWORD": "<secret>",
"PINOT_TOKEN": "<secret>",
"PINOT_USE_MSQE": "<value>",
"MCP_TRANSPORT": "<value>",
"AUTH_PROVIDER": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More developer servers
| Server | Runs |
|---|---|
| AntoskillA package manager for Agent Skills — discover, vet, and pin them across Claude Code and Codex. | Local · stdio |
| AntriebValidates AI infra code on real VMs. Self-corrects until it works. No containers, no sandboxes. | Remote · HTTP |
| AnybrowseConverts any URL to clean, LLM-ready Markdown using real Chrome browsers. | Remote · HTTP |
| AnySkillsAnySkills online school: build courses, lessons and tests, publish, track student progress. | Remote · HTTP |
| Apex (smartapex.uk) AI Component Card StoreRun verified read-only code tools: quant diagnostics + agent-ops preflight, no source exposure. | Remote · HTTP |
| API Key CaseLocal MCP tools for secret status and guarded deployment. Values never reach the agent. | Local · stdio |
| API LockerEncrypted credential vault: LLM, service & OAuth keys. 21-tool MCP server for your AI agent. | Local · stdio |
| API Status CheckLive status probes plus published uptime and incident history for 280+ APIs and cloud services. | Remote · HTTP |