[ MCP SERVER SUMMARY ]
StarTree's MCP server for Apache Pinot lets AI agents query and explore real-time analytics tables. Bifrost governs which Pinot tools and clusters each team can reach and keeps query activity in your gateway audit log.
| Property | Details |
|---|---|
| Company | StarTree |
| Connection type | STDIO |
| Authentication | Pinot cluster credentials (as configured) |
| Package or endpoint | mcp-pinot (StarTree) |
| Capabilities | Realtime analytics queries, Pinot table exploration, Cluster metadata access |
| Official documentation | Apache Pinot MCP documentation |
[ HOW TO CONNECT ]
Start the gateway locally or deploy in your VPC.
npx -y @maximhq/bifrost
Open MCP Gateway in the Bifrost dashboard, click New MCP Server, and choose STDIO. Or register via the API below.
• Confirm the current package name and required PINOT_* env vars in the StarTree mcp-pinot README before production use.
• Point Bifrost STDIO env at your controller/broker endpoints.
Configure Claude Desktop, Cursor, or Claude Code to use your Bifrost endpoint with a virtual key instead of connecting directly to Apache Pinot.
{
"mcpServers": {
"bifrost": {
"url": "http://localhost:8080/mcp",
"headers": {
"Authorization": "Bearer vk_your_virtual_key"
}
}
}
}[ EXAMPLE CONFIG ]
Add this MCP client with a POST to /api/mcp/client. See Connecting to MCP Servers for full options.
curl -X POST http://localhost:8080/api/mcp/client \
-H "Content-Type: application/json" \
-d '{
"name": "apache-pinot",
"connection_type": "stdio",
"stdio_config": {
"command": "uvx",
"args": [
"mcp-pinot"
]
},
"tools_to_execute": [
"*"
]
}'[ WHY BIFROST ]
Virtual keys, RBAC, and tool allowlists per team or agent.
Attribute MCP tool spend alongside LLM usage in one view.
Log every tool call with latency, server, and virtual key metadata.
Upstream secrets stay in the gateway — not on every laptop.
[ FAQ ]
Apache Pinot exposes realtime analytics queries, pinot table exploration, cluster metadata access to MCP-compatible AI clients. Bifrost connects to it as an upstream MCP client and exposes approved tools through one governed /mcp endpoint.
Apache Pinot uses Pinot cluster credentials (as configured). Store credentials in Bifrost's environment or credential configuration so they stay at the gateway instead of being copied into every AI client.
Yes. After registering Apache Pinot in Bifrost, point any HTTP MCP-compatible client at the Bifrost /mcp endpoint and authenticate with a virtual key. The client sees only the tools allowed for that key.
[ RELATED SERVERS ]
Connect AI agents to Snowflake data and services through Snowflake Labs’ official MCP server.
Give AI agents access to Honeycomb observability data for investigating production systems, traces, and telemetry.
An MCP server enabling AI assistants to interact with Anytype - a local and collaborative wiki - to organize objects, lists, and more through natural language.