Confluent MCP Server

Official

Manage Confluent Cloud, Confluent Platform & Apache Kafka via natural language — 50+ tools across Kafka, Flink, Schema Registry & more.

Unverified

stdio (local)

API key

TypeScript

View repo 160 npm

Add to your client

Copy the config for your MCP client and paste it into its config file.

Install / run

npx -y @confluentinc/mcp-confluent

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

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

Step-by-step guides: Add to Claude Desktop · Add to Cursor · Add to Windsurf

Before you start

Node.js 22 or later
A config.yaml file (generate with `npx @confluentinc/mcp-confluent --init-config`)
For Confluent Cloud: a Confluent Cloud account with API keys, or OAuth sign-in credentials
For local/Confluent Platform: a Kafka and/or Schema Registry endpoint
pnpm only if building from source

About Confluent MCP Server

Confluent MCP Server connects MCP-compatible AI clients to Confluent Cloud, Confluent Platform, and standalone Apache Kafka. It provides 50+ tools across Kafka, Flink SQL, Schema Registry, Connectors, Tableflow, catalog/tags, metrics, and billing. Configuration is YAML-based (bootstrap with --init-config), tools are auto-enabled by the service blocks present in your config, and authentication uses static API keys or OAuth (PKCE). The server runs over stdio by default and optionally HTTP/SSE.

Tools & capabilities (71)

search-product-docs

Search Confluent product documentation (docs.confluent.io, developer.confluent.io, support.confluent.io) by keyword.

get-product-doc-page

Fetch the full markdown content of a Confluent product documentation page.

explain-disabled-tools

Explain why a tool is missing or unavailable (e.g., why a Kafka tool can't be listed).

list-configured-connections

List every configured connection and the connection-routable tools you can invoke against each.

describe-configured-connection

Describe one configured connection by id: its non-secret config (type, endpoints, resource ids) and tool availability.

list-topics

List all topics in the Kafka cluster.

create-topics

Create one or more Kafka topics with an optional partition count and replication factor.

delete-topics

Delete the topics with the given names.

produce-message

Produce records to a Kafka topic. Supports Confluent Schema Registry serialization (AVRO, JSON, PROTOBUF) for keys and values.

consume-messages

Consume messages from Kafka topics. Optionally restrict to a partition and start from an offset, timestamp, earliest, or latest.

list-consumer-groups

List consumer groups on a Kafka cluster (wraps the broker's listGroups admin call), with optional filters.

describe-consumer-group

Describe a single consumer group on a Kafka cluster: state, type, protocol, partition assignor, and members.

get-consumer-group-lag

Compute live offset lag for a single Kafka consumer group, per (topic, partition).

get-partition-offsets

Return per-partition low/high watermarks and message counts for a Kafka topic.

alter-topic-config

Alter topic configuration in Confluent Cloud.

get-topic-config

Retrieve configuration details for a specific Kafka topic.

create-flink-statement

Make a request to create a Flink SQL statement.

list-flink-statements

Retrieve a sorted, filtered, paginated list of all Flink statements.

read-flink-statement

Make a request to read a Flink statement and its results.

delete-flink-statements

Make a request to delete a Flink statement.

get-flink-statement-exceptions

Retrieve the 10 most recent exceptions for a Flink SQL statement.

check-flink-statement-health

Perform an aggregate health check for a Flink SQL statement (healthy/warning/critical).

detect-flink-statement-issues

Detect issues for a Flink SQL statement by analyzing status, exceptions, and performance metrics.

get-flink-statement-profile

Get Query Profiler data for a Flink SQL statement, including the task graph and performance metrics.

list-flink-catalogs

List all catalogs available in the Flink environment via INFORMATION_SCHEMA.CATALOGS.

list-flink-databases

List all databases (schemas) in a Flink catalog via INFORMATION_SCHEMA.SCHEMATA.

list-flink-tables

List all tables in a Flink database via INFORMATION_SCHEMA.TABLES.

describe-flink-table

Get full schema details for a Flink table via INFORMATION_SCHEMA.COLUMNS.

get-flink-table-info

Get table metadata via INFORMATION_SCHEMA.TABLES: watermark configuration, distribution info, and table type.

list-connectors

Retrieve a list of names of the active connectors.

get-connector-config

Retrieve the full configuration map for a connector.

get-connector-offsets

Retrieve current offsets for a connector's tasks.

get-connector-status

Get the current state of a connector and its tasks (RUNNING, FAILED, PAUSED, UNASSIGNED) including failure traces.

get-connector-tasks

List the tasks of a connector along with their configurations.

get-connector-error-summary

Summarize a connector's current errors in a compact, agent-friendly form.

get-connector-error-recommendations

Get suggested remediation steps for a connector that has failed or is in an error state.

get-connector-logs

Retrieve recent log entries for a Confluent Cloud connector from the Cloud logging API.

create-connector

Create a new connector. Returns the new connector information if successful.

delete-connector

Delete an existing connector.

pause-connector

Pause a running connector and its tasks (idempotent).

resume-connector

Resume a paused connector and its tasks (idempotent).

restart-connector

Restart a connector and its tasks (asynchronous).

update-connector-config

Update the configuration of an existing connector (full-replace).

list-schemas

List all schemas in the Schema Registry.

create-schema

delete-schema

Delete a schema subject or a specific version from the Schema Registry.

search-topics-by-tag

List all topics in the Kafka cluster with the specified tag.

search-topics-by-name

List all topics in the Kafka cluster matching the specified name.

create-topic-tags

Create new tag definitions in Confluent Cloud.

delete-tag

Delete a tag definition from Confluent Cloud.

remove-tag-from-entity

Remove a tag from an entity in Confluent Cloud.

add-tags-to-topic

Assign existing tags to Kafka topics in Confluent Cloud.

list-tags

Retrieve all tags with definitions from Confluent Cloud Schema Registry.

list-organizations

List Confluent Cloud organizations the current credentials can see (paginated).

list-environments

Get all environments in Confluent Cloud with pagination support.

read-environment

Get details of a specific environment by ID.

list-clusters

Get all clusters in the Confluent Cloud environment.

create-tableflow-topic

Make a request to create a Tableflow topic.

list-tableflow-topics

Retrieve a sorted, filtered, paginated list of all Tableflow topics.

read-tableflow-topic

Make a request to read a Tableflow topic.

update-tableflow-topic

Make a request to update a Tableflow topic.

delete-tableflow-topic

Make a request to delete a Tableflow topic.

list-tableflow-regions

Retrieve a sorted, filtered, paginated list of all Tableflow regions.

create-tableflow-catalog-integration

Make a request to create a Tableflow catalog integration (e.g., AWS Glue).

list-tableflow-catalog-integrations

Retrieve a sorted, filtered, paginated list of all catalog integrations.

read-tableflow-catalog-integration

Make a request to read a Tableflow catalog integration.

update-tableflow-catalog-integration

Make a request to update a Tableflow catalog integration.

delete-tableflow-catalog-integration

Make a request to delete a Tableflow catalog integration.

list-available-metrics

List available Confluent Cloud metrics and their filter fields from the Telemetry API. Use before query-metrics.

query-metrics

Query Confluent Cloud metrics from the Telemetry API.

list-billing-costs

Retrieve billing cost data for a Confluent Cloud organization within a specified date range (paginated).

What this server can do

Confluent MCP Server provides tools for these capabilities — tap one to see every MCP server that does the same:

Inspect database schema

When to use it

Manage Kafka topics, produce/consume messages, and inspect consumer group lag from an AI assistant
Author, run, and diagnose Flink SQL statements with health checks and query profiling
Inspect and manage Kafka Connect connectors, including error summaries and remediation recommendations
Register and manage Schema Registry schemas (AVRO, JSON, PROTOBUF)
Organize and search topics with catalog tags
Query Confluent Cloud operational metrics and billing costs
Operate self-managed Confluent Platform or local Kafka clusters during development

Security notes

Authenticates to Confluent Cloud via static API keys in config.yaml or OAuth (PKCE). For HTTP/SSE transports, generate an API key with `npx @confluentinc/mcp-confluent --generate-key` and set it under server.auth.api_key; --disable-auth should only be used in development. Includes DNS rebinding protection via --allowed-hosts. Telemetry is collected by default and can be disabled with DO_NOT_TRACK=true.

Confluent MCP Server FAQ

Is this an official Confluent project?

Yes. It is published by the confluentinc organization on GitHub and distributed as the npm package @confluentinc/mcp-confluent under the MIT license.

How do I authenticate to Confluent Cloud?

Two ways: static API keys defined in config.yaml, or OAuth (PKCE) which opens a browser sign-in on the first tool call that needs Confluent access. OAuth currently covers a subset of tool categories (Kafka, Schema Registry, Cloud resource listing, Billing); the rest still require a direct connection with static API keys.

Why don't all the tools show up?

Tools are auto-enabled based on which service blocks are present in your resolved config.yaml. Run `npx @confluentinc/mcp-confluent --list-tools` or invoke the explain-disabled-tools MCP tool to see which are active and why others are absent.

Which transports are supported?

stdio (default), plus optional http and sse. Select them with the --transport flag, e.g. --transport http,sse,stdio.

Can I use it with local Kafka or Confluent Platform instead of Confluent Cloud?

Yes. Point a 'direct' connection at your brokers and Schema Registry. Local/CP deployments expose the Kafka and Schema Registry tools; the Confluent Cloud-only tools (Flink, Tableflow, Billing, Metrics) stay disabled.

#kafka #confluent #flink #schema-registry #kafka-connect #streaming #tableflow #data

Alternatives to Confluent MCP Server

Compare all alternatives →

MCP Toolbox for Databases (BigQuery)

Databases

16k

Google's official MCP server with prebuilt BigQuery tools, querying datasets via Application Default Credentials.

Verified

stdio (local)

OAuth

10 tools

Updated 15 days agoRepo

Postgres MCP Pro

Databases

2.9k

Read/write Postgres access plus index tuning, EXPLAIN plans, and database health analysis for AI agents.

Verified

stdio (local)

API key

Python

9 tools

Updated 3 months agoRepo

Supabase MCP Server

Databases

2.7k

Official Supabase server: manage tables, run SQL, branches, configs and edge functions from your AI client.

Verified

HTTP (remote)

OAuth

TypeScript

12 tools

Updated 1 month agoRepo

Compare Confluent MCP Server with:

vs MCP Toolbox for Databases (BigQuery)vs Postgres MCP Pro vs Supabase MCP Server vs Neon MCP Server