Name: Confluent Cloud
Author: confluentinc

LABSCO SUMMARY

The tool list is a readout of your configuration, and the server will tell you exactly which block is missing.

On a bare config you get documentation and diagnostics; everything else appears per connection once the config it needs is present. That inversion turns the usual guessing game into a lookup — one tool takes a tool name and returns the YAML that would unlock it, another groups every gap by the piece of config it waits on, and neither writes to your file. If you are a Confluent Cloud customer and want none of this, Confluent also runs a managed server; this one is the answer for Confluent Platform, self-managed Kafka, or a toolset you intend to trim yourself.

What it is

Confluent's open-source server for Confluent Cloud, Confluent Platform and standalone Kafka. Documentation and diagnostics are always present; the Kafka, Flink, Schema Registry, Connector, Tableflow, Metrics and Billing tools switch on per connection as the configuration for them appears.

What you get

Kafka worked from the client: topics listed, created, deleted and reconfigured, messages produced and consumed, consumer groups described with their lag
Flink SQL statements created, listed, deleted and read back, with catalogs, databases and table schemas explored, plus health checks, issue detection and a query profile
Connectors inspected and managed — status, tasks, offsets, logs, an error summary and suggested remediation, then pause, resume, restart or reconfigure
Schema Registry subjects listed, registered and deleted, and topics organised and searched by tag
Tableflow topics and catalog integrations created and managed, alongside Confluent Cloud metrics and billing costs
Keyword search across docs.confluent.io, developer.confluent.io and support.confluent.io, then the full markdown of any result page — available on a bare config with no credentials
Diagnostics that explain the tool list itself: every configured connection with the tools routable against it and whether it is read-only, the unavailable ones bucketed by the config each is waiting on, and a copy-pasteable YAML snippet for the tool you want to unlock

Requirements

Node.js 22.19.0 or later, and a YAML configuration — the CLI writes a starter one for you. Confluent Cloud takes either static API keys per service block or an OAuth sign-in in the browser, which covers most tool groups but not all of them yet; a local Kafka or Confluent Platform needs only bootstrap servers and a Schema Registry endpoint. Which tools appear follows the blocks you fill in, and allow and block lists trim the surface further. Over HTTP or SSE the server wants an API key of its own, generated by the CLI. Tableflow additionally needs IAM permissions granted in your cloud account before any of its calls succeed. Usage data and error reports are sent unless DO_NOT_TRACK=true. MIT, community-supported.

Setup effort

One command — npx @confluentinc/mcp-confluent --config ./config.yaml

See installation options

USE CASES

Working out why the Kafka tools never appeared

Ask which tools are unavailable and what each is waiting on, then ask for the YAML that would unlock the one you actually need. The snippet comes back per connection and is yours to paste — the server never edits the file.

explain-disabled-toolsconfig-help

Checking what a connection can do before routing a call to it

List the connections to get their ids and their read-only flags, then describe the one you mean: its non-secret config and, tool by tool, the gap or policy keeping anything unavailable off.

list-configured-connectionsdescribe-configured-connection

Reading the Confluent docs without leaving the client

Search the three documentation domains by keyword, then pull the full markdown of the page worth reading rather than working from a snippet.

search-product-docsget-product-doc-page

Cutting the catalogue down before an agent sees it

Fill in only the service blocks the job needs, and use the allow and block lists on top, so a client with a tool budget is not handed fifty of them.

list-configured-connectionsexplain-disabled-tools

6 tools

Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.

`config-help`

Call when the user wants to enable or unlock a specific tool (e.g. "how do I enable the tableflow tools?", "what config does create-flink-statement need?", "why isn't list-topics showing up — fix it"). Given a tool name, returns a copy-pasteable YAML snippet, per connection, that closes the gap between the current config and what that tool requires. Suggests only — it never edits your config file. Prefer explain-disabled-tools when the question is "what's off and why?" across all tools; prefer this when the user has a target tool in mind and wants the exact YAML to add.

INSTALLATION

Connect your client

Server setup

TERMINAL

npx @confluentinc/mcp-confluent --config ./config.yaml

MCP Clients

Claude Code, Cursor, Windsurf

JSON

{
  "mcpServers": {
    "confluent": {
      "command": "npx",
      "args": [
        "-y",
        "@confluentinc/mcp-confluent",
        "--config",
        "<YOUR_PATH_TO_CONFIG>"
      ]
    }
  }
}

Credentials do not go in the client block. They live in the config.yaml that --config points to (npx @confluentinc/mcp-confluent --init-config writes a starter): an API key and secret per service block, usually written as ${KAFKA_API_KEY}, ${KAFKA_API_SECRET}, ${SCHEMA_REGISTRY_API_KEY} and ${SCHEMA_REGISTRY_API_SECRET} and read from your environment (or from a dotenv file passed with -e). Confluent Cloud can use an OAuth browser sign-in instead of static keys, and a local Kafka or Schema Registry needs no keys at all.

Claude Desktop

CLAUDE DESKTOP · JSON

{
  "mcpServers": {
    "confluent": {
      "command": "npx",
      "args": [
        "-y",
        "@confluentinc/mcp-confluent",
        "--config",
        "<YOUR_PATH_TO_CONFLUENT_MCP_SERVER>/config.yaml"
      ]
    }
  }
}

Gemini CLI

GEMINI CLI · TERMINAL

gemini extensions install https://github.com/confluentinc/mcp-confluent

Goose

GOOSE · TERMINAL

goose configure

Select Add extension, choose Command-line Extension, and enter mcp-confluent as the extension name

GOOSE

mcp-confluent

When it asks for the command, enter:

GOOSE · TERMINAL

npx -y @confluentinc/mcp-confluent --config <YOUR_PATH_TO_CONFLUENT_MCP_SERVER>/config.yaml

IBM Bob

IBM BOB · JSON

{
  "mcpServers": {
    "confluent": {
      "command": "npx",
      "args": [
        "-y",
        "@confluentinc/mcp-confluent",
        "-c",
        "/Users/<YOUR_USERNAME>/<YOUR_PATH_TO_CONFIG>/myconfig.yaml"
      ]
    }
  }
}

VS Code

VS CODE · JSON

{
  "servers": {
    "confluent": {
      "command": "npx",
      "args": [
        "-y",
        "@confluentinc/mcp-confluent",
        "--config",
        "<YOUR_PATH_TO_CONFIG>"
      ]
    }
  }
}

Confluent Cloud

The tool list is a readout of your configuration, and the server will tell you exactly which block is missing.

What it is

What you get

Requirements

Setup effort

Working out why the Kafka tools never appeared

Checking what a connection can do before routing a call to it

Reading the Confluent docs without leaving the client

Cutting the catalogue down before an agent sees it

6 tools

`config-help`

`describe-configured-connection`

`explain-disabled-tools`

`get-product-doc-page`

`list-configured-connections`

`search-product-docs`

What to know first

Tools you get

Requires

Connect your client

Server setup

MCP Clients

Claude Code, Cursor, Windsurf

Claude Desktop

Gemini CLI

Goose

IBM Bob

VS Code

Confluent Cloud

The tool list is a readout of your configuration, and the server will tell you exactly which block is missing.

What it is

What you get

Requirements

Setup effort

Working out why the Kafka tools never appeared

Checking what a connection can do before routing a call to it

Reading the Confluent docs without leaving the client

Cutting the catalogue down before an agent sees it

6 tools

config-help

describe-configured-connection

explain-disabled-tools

get-product-doc-page

list-configured-connections

search-product-docs

What to know first

Tools you get

Requires

Connect your client

Server setup

MCP Clients

Claude Code, Cursor, Windsurf

Claude Desktop

Gemini CLI

Goose

IBM Bob

VS Code

Same category

Lenses

Airflow-API MCP

Kafka TypeScript MCP Server

Kafka Schema Drift Auto-Fixer

`config-help`

`describe-configured-connection`

`explain-disabled-tools`

`get-product-doc-page`

`list-configured-connections`

`search-product-docs`