Metabase MCP
Security scan passedLets your agent search, query and chart the data in your own Metabase, and build questions and dashboards with your permissions.

Confluent's open-source MCP server for Gemini CLI: work with Kafka topics, Flink SQL, connectors and schemas in plain words.
by Confluent· Data & analyticsUnclaimed · Yours? Claim it
4 images
About
Confluent's open-source MCP server, packaged as a Gemini CLI extension. It lets your agent work with Confluent Cloud, Confluent Platform and self-managed Apache Kafka in plain words: topics and messages, Flink SQL, Schema Registry, connectors, Tableflow and more. What you can do with it - List, create and delete Kafka topics, produce and consume messages, and check consumer groups and their lag - Create and manage Flink SQL statements, explore Flink catalogs and tables, and check a statement's health - List, register and delete schemas in Schema Registry - Inspect and manage Kafka Connect connectors, with error summaries, suggested fixes and logs - Tag and search topics, and manage Tableflow topics and catalog integrations - Find your Confluent Cloud environments and clusters, and query metrics and billing costs - Search Confluent's product documentation How it connects - Install it with gemini extensions install https://github.com/confluentinc/mcp-confluent. It runs Confluent's @confluentinc/mcp-confluent package on your machine with npx, and needs Node.js 22.19.0 or later. - The extension reads its settings from a .env file in its folder, ~/.gemini/extensions/mcp-confluent/.env: your Kafka bootstrap servers, Confluent Cloud API keys and the endpoints for each service you use. - Each group of tools turns on only when its settings are there. For a local Kafka or Confluent Platform cluster, the Kafka and Schema Registry tools need only their endpoints. Good to know - When the server runs with a config.yaml file instead, it can sign in to Confluent Cloud through your browser (OAuth) rather than with API keys. The Gemini extension currently uses the .env file. - Confluent Cloud customers can also use Confluent's fully managed MCP server. This open-source server is community-supported, and Confluent's support for it is best-effort. - It sends usage data and error reports to Confluent. Set DO_NOT_TRACK=true to opt out.
Once it’s added
“List the topics in my Kafka cluster.”
“Create a topic called orders with six partitions.”
“Show me the latest messages on the orders topic.”
“How far behind is the payments consumer group?”
Before you add it
Reads only
Topics, messages, consumer groups and their lag · Flink statements, catalogs and tables · Connector status, errors and logs · Confluent Cloud metrics and billing costs
Makes changes · your agent can ask first
Creates and deletes topics, and produces messages · Creates and deletes Flink SQL statements · Creates, pauses, restarts or deletes connectors · Registers or deletes schemas, and manages tags and Tableflow topics
From people who use it
Step by step
Nothing new reaches your agent until a person has looked at it.
Plugins people install alongside Confluent MCP Server.
No reviews yet. Used Confluent MCP Server? Say how it went.
Write a reviewRuns on your machine.
gemini extensions install https://github.com/confluentinc/mcp-confluent
Scanned and passed · checked 6 h ago
Plugins people install alongside Confluent MCP Server.
Lets your agent search, query and chart the data in your own Metabase, and build questions and dashboards with your permissions.
Equips your coding agent with a data engineer, pipeline commands and skills for Airflow, dbt, Spark and data quality.
Lets your agent query your PostHog analytics, triage errors, and create feature flags and experiments from plain-language asks.
Data analytics skills for product managers: SQL from plain English, cohort retention analysis and A/B test reads with a ship-or-stop call.
Nobody has shared how they use Confluent MCP Server yet.
“Why is my connector failing, and how do I fix it?”
“Check the health of my Flink SQL statement.”
Scanned on every change, and again when our rules improve.
Tell us and a person on the trust team will look at it. Or email [email protected].
Security scan
Passed
Safe to install in every agent it supports. Extensions.