Submit Log in

Confluent

by Confluent

v1.5.0

MIT

Repository Docs npm

Databases & Data

kafkastreamingflinkschema-registryconfluent

Summary

Open-source MCP server for Confluent Cloud, Confluent Platform and standalone Apache Kafka — 50+ tools spanning topics, Flink SQL, Schema Registry, connectors and Tableflow.

Features

50+ tools across Kafka, Flink SQL, Schema Registry, connectors and Tableflow
Works against Confluent Cloud, Confluent Platform and standalone Apache Kafka
Tools auto-enable from the service blocks present in your config file
OAuth or API-key authentication for Confluent Cloud
--init-config scaffolding and --list-tools discovery from the CLI

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

Open your agent's MCP configuration file.
Merge the snippet below into it.
Restart the agent — the "Confluent" tools will be available.

{
  "mcpServers": {
    "confluent": {
      "command": "npx",
      "args": [
        "-y",
        "@confluentinc/mcp-confluent",
        "--config",
        "/absolute/path/to/config.yaml"
      ]
    }
  }
}

Claude Code

Add the server with a single CLI command.

claude mcp add confluent -- npx -y @confluentinc/mcp-confluent --config /absolute/path/to/config.yaml

Claude Desktop

Add the server to claude_desktop_config.json (Settings → Developer → Edit Config).

{
  "mcpServers": {
    "confluent": {
      "command": "npx",
      "args": [
        "-y",
        "@confluentinc/mcp-confluent",
        "--config",
        "/absolute/path/to/config.yaml"
      ]
    }
  }
}

Cursor

{
  "command": "npx",
  "args": [
    "-y",
    "@confluentinc/mcp-confluent",
    "--config",
    "/absolute/path/to/config.yaml"
  ]
}

Description

A Kafka cluster is an awkward thing to inspect conversationally: the state you want is spread across topics, schemas, connectors and stream-processing jobs, each with its own CLI. Confluent's MCP server collapses that into one tool surface an assistant can drive, covering Confluent Cloud, self-managed Confluent Platform and plain Apache Kafka deployments.

Scope

More than 50 tools across Kafka (topics, partitions, consumer groups, produce and consume), Flink SQL statements, Schema Registry, connectors, and Tableflow. Tools are enabled dynamically based on which service blocks appear in your resolved configuration, so a local-Kafka setup does not get cluttered with Confluent Cloud tooling it cannot use.

Getting started

Node.js 22.19.0 or newer. Generate a starter configuration, fill in your connection details, and run it:

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

npx -y @confluentinc/mcp-confluent --list-tools prints the full tool inventory. OAuth authentication is supported for Confluent Cloud alongside API keys.

Which server to use

Confluent Cloud customers also have a fully managed MCP server with no local process and no dependencies, governed by existing RBAC permissions and including AI-powered connector diagnostics. Reach for this open-source server when you need Confluent Platform or self-managed Kafka support, or want to customise and extend the toolset.

Support status

Confluent describes the open-source server as a community-supported project: support is best-effort with no service level commitments, and issues go to the GitHub repository rather than Confluent support. MIT licensed. Works with Claude Desktop, Claude Code, Cursor, VS Code, Goose and Gemini CLI.

Related MCP Servers

MCP: Amplitude MCP Server

by Amplitude

New

Amplitude's official hosted MCP server with 50+ tools over analytics, cohorts, experiments, feature flags, taxonomy and session replay, secured by OAuth and existing RBAC roles.

Databases & DataProductivity

MCP: deja-vu

by Vladislav Shulcz

New

Indexes the coding-agent sessions already sitting on your disk — months of history from before you installed it — and serves them back over MCP. 3.5 GB searched in ~1.5 ms, no LLM, no embeddings.

Developer ToolsDatabases & Data

MCP: Weaviate MCP Server

by Weaviate

New

Weaviate's MCP server, built into the database itself — hybrid search, schema inspection, tenant listing and batch upserts at /v1/mcp, scoped by RBAC.

Databases & Data

MCP: MCP Toolbox for Databases

by Google

Featured

Google's open-source MCP server for enterprise databases — one binary that fronts AlloyDB, BigQuery, Spanner, Postgres, MySQL, Oracle, MongoDB, Snowflake and more.

Databases & DataCloud & Infrastructure

Browse all MCP servers →