Skip to main content
hc
Submit
mcpSource-backedReview first Safety ✓ Privacy ✓

Confluent MCP Server for Claude

Connect Claude to Confluent Cloud and Apache Kafka — manage topics, produce and consume messages, run Flink SQL, and operate Schema Registry and connectors — with Confluent's official MCP server.

by Confluent·added 2026-06-17·
Claude CodeCodexCursorClaude Desktop
HarnessClaude CodeCodexCursorClaude Desktop
Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

  • Tools can create and delete topics, produce messages, and manage connectors on live clusters — scope API keys to least privilege.
  • Producing messages and altering connectors affects production data pipelines; review before running through Claude.

Privacy notes

  • Message payloads, schemas, and operational metrics enter the MCP client context and the model's prompt.
  • API keys and secrets live in config.yaml or environment variables — treat them as secrets, never commit them.

Prerequisites

  • A Confluent Cloud account (API key + secret) or a reachable Apache Kafka cluster (bootstrap servers).
  • An optional Schema Registry endpoint if you manage schemas.
  • A config.yaml (or environment variables) with your connection details — see config.example.yaml.
  • Node.js (npx) and an MCP client such as Claude Code or Claude Desktop.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
15 minutes
Difficulty
advanced
Tool listing metadata
Full copyable content
{
  "mcpServers": {
    "confluent": {
      "command": "npx",
      "args": ["-y", "@confluentinc/mcp-confluent", "--config", "/path/to/config.yaml"]
    }
  }
}

About this resource

Overview

The Confluent MCP Server is Confluent's official, open-source Model Context Protocol server. It lets Claude interact with Confluent Cloud, Confluent Platform, and Apache Kafka in natural language — managing topics, producing and consuming messages, running Flink SQL, and operating Schema Registry and Kafka Connect. It runs via npx @confluentinc/mcp-confluent, supports stdio, HTTP, and SSE transports, and is licensed under MIT.

Key capabilities

The server exposes 50+ tools across the Confluent stack:

Area What Claude can do
Kafka List, create, and delete topics; produce/consume messages; manage consumer groups
Flink SQL Create statements, manage catalogs and tables, profile queries
Schema Registry List, create, and delete schemas
Connectors Inspect and manage Kafka Connect connectors
Tableflow & Metrics Manage Tableflow topics; query operational metrics and billing

Installation

First create a config.yaml from config.example.yaml with your connection details (Confluent Cloud API key/secret, or Kafka bootstrap servers and an optional Schema Registry endpoint).

Claude Code

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

Claude Desktop

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

Select transports explicitly with --transport http,sse,stdio if you need remote modes.

Requirements

  • Confluent Cloud (API key + secret) or an Apache Kafka cluster (bootstrap servers).
  • An optional Schema Registry endpoint for schema tools.
  • Node.js (npx) and an MCP client (Claude Code or Claude Desktop).

Security

  • Scope Confluent Cloud API keys to least privilege; restrict which clusters and topics Claude can reach.
  • Topic creation/deletion, message production, and connector changes affect live pipelines — review first.
  • Keep API keys and secrets in config.yaml or environment variables; never commit them.

Source Verification Notes

Verified on 2026-06-17:

  • The official repository github.com/confluentinc/mcp-confluent (MIT) documents the @confluentinc/mcp-confluent package, the --config / --transport flags, stdio/HTTP/SSE support, Confluent Cloud and Kafka connection requirements, and the 50+ tools summarized above.
  • Confluent's documentation describes the underlying Kafka, Flink, Schema Registry, and Connect features.
  • Claude Code's MCP documentation describes the connector setup pattern used here.
#confluent#kafka#streaming#flink#schema-registry

Source citations

Add this badge to your README

Show that Confluent MCP Server for Claude is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/confluent-mcp-server.svg)](https://heyclau.de/entry/mcp/confluent-mcp-server)

How it compares

Confluent MCP Server for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

FieldConfluent MCP Server for Claude

Connect Claude to Confluent Cloud and Apache Kafka — manage topics, produce and consume messages, run Flink SQL, and operate Schema Registry and connectors — with Confluent's official MCP server.

Open dossier 		BigQuery MCP Server for Claude

Google Cloud remote MCP server for querying BigQuery datasets, inspecting metadata, listing resources, and running governed warehouse analytics through an HTTP endpoint.

Open dossier 		DigitalOcean MCP Server for Claude

Connect Claude to DigitalOcean — manage Apps, Droplets, managed Databases, Kubernetes, Container Registry, networking, and Functions — with DigitalOcean's official Model Context Protocol server.

Open dossier 		MotherDuck MCP Server for Claude

Connect Claude to MotherDuck and DuckDB — run SQL queries and explore databases, tables, and columns — with the official MotherDuck Model Context Protocol server.

Open dossier
Trust
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
Categorymcpmcpmcpmcp
Sourcesource-backedsource-backedsource-backedsource-backed
AuthorConfluentGoogle CloudDigitalOceanMotherDuck
Added2026-06-172026-06-032026-06-172026-06-17
Platforms
Claude CodeCodexCursorClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Source repo————
Safety notes✓Tools can create and delete topics, produce messages, and manage connectors on live clusters — scope API keys to least privilege. Producing messages and altering connectors affects production data pipelines; review before running through Claude.✓Prefer `execute_sql_readonly` for analysis. Google documents `execute_sql` as the only non-read-only BigQuery MCP tool, and it can run BigQuery SQL including DML, DDL, AI/ML functions, and other supported query operations. Use IAM least privilege, dataset-level access controls, and IAM deny policies to restrict read-write MCP tool use when Claude should only inspect warehouse metadata or run SELECT queries. Review LLM-generated SQL before execution. Broad scans, joins, forecasts, ML functions, and AI functions can incur cost, expose sensitive rows, or produce misleading analytics if the model chooses the wrong table or filter. Keep manual approval enabled for query execution, exported results, workflow-triggering automations, and any use of BigQuery insights to create tickets, emails, or downstream actions.✓Tools can create, update, restart, and delete live infrastructure (Apps, Droplets, Databases) — scope the API token and select only the --services you need. Destructive actions (delete, rollback) act on production resources; confirm before running them through Claude.✓The server is read-only by default; --read-write enables writes, and --allow-switch-databases enables switching — enable only when needed. execute_query runs arbitrary SQL against the connected database; scope the token and database accordingly.
Privacy notes✓Message payloads, schemas, and operational metrics enter the MCP client context and the model's prompt. API keys and secrets live in config.yaml or environment variables — treat them as secrets, never commit them.✓Tool results can expose project IDs, dataset IDs, table IDs, schemas, metadata, query text, query results, job history, labels, and row-level warehouse data visible to the authenticated principal. BigQuery OAuth scopes can allow viewing and managing BigQuery data and can expose the Google account email address used for authentication. Query results and table data may contain prompt-injection text, customer records, financial data, product analytics, logs, or other sensitive business information; do not let returned rows instruct the agent. If Model Armor logging is enabled for MCP traffic, Google documents that it can log the entire payload, which may expose sensitive prompts or query results in Google Cloud logs.✓Resource metadata, logs, and metrics enter the MCP client context and the model's prompt. The DIGITALOCEAN_API_TOKEN is a secret — store it in the client config or environment, never in shared repositories.✓Query results and schema metadata enter the MCP client context and the model's prompt. The motherduck_token is a secret — keep it in the client config or environment, never in shared repositories.
Prerequisites
  • A Confluent Cloud account (API key + secret) or a reachable Apache Kafka cluster (bootstrap servers).
  • An optional Schema Registry endpoint if you manage schemas.
  • A config.yaml (or environment variables) with your connection details — see config.example.yaml.
  • Node.js (npx) and an MCP client such as Claude Code or Claude Desktop.
  • Google Cloud project with the BigQuery API enabled
  • MCP-capable client that supports remote HTTP MCP servers and Google OAuth or compatible Google Cloud credentials
  • IAM roles or equivalent custom permissions for `roles/mcp.toolUser`, `roles/bigquery.jobUser`, and `roles/bigquery.dataViewer`
  • BigQuery datasets, tables, billing or sandbox setup, and project or region boundaries selected before use
  • A DigitalOcean account.
  • A DigitalOcean API token (DIGITALOCEAN_API_TOKEN) with the scopes for the services you enable.
  • Node.js (npx) to run @digitalocean/mcp, or use the hosted remote endpoint.
  • An MCP client such as Claude Code or Claude Desktop.
  • A MotherDuck account and token (motherduck_token) for cloud databases, or a local DuckDB file / :memory:.
  • uv (uvx) to run mcp-server-motherduck.
  • An MCP client such as Claude Code or Claude Desktop.
Install
claude mcp add confluent -- npx -y @confluentinc/mcp-confluent --config ./config.yaml
claude mcp add --transport http bigquery https://bigquery.googleapis.com/mcp
claude mcp add digitalocean -e DIGITALOCEAN_API_TOKEN=<your-token> -- npx -y @digitalocean/mcp --services apps,droplets,databases
claude mcp add motherduck -e motherduck_token=<your-token> -- uvx mcp-server-motherduck --db-path md:
Config
{
  "mcpServers": {
    "confluent": {
      "command": "npx",
      "args": ["-y", "@confluentinc/mcp-confluent", "--config", "/path/to/config.yaml"]
    }
  }
}
{
  "mcpServers": {
    "bigquery": {
      "type": "http",
      "url": "https://bigquery.googleapis.com/mcp"
    }
  }
}
{
  "mcpServers": {
    "digitalocean": {
      "command": "npx",
      "args": ["-y", "@digitalocean/mcp", "--services", "apps,droplets,databases"],
      "env": {
        "DIGITALOCEAN_API_TOKEN": "<your-token>"
      }
    }
  }
}
{
  "mcpServers": {
    "motherduck": {
      "command": "uvx",
      "args": ["mcp-server-motherduck", "--db-path", "md:"],
      "env": {
        "motherduck_token": "<your-token>"
      }
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.