Skip to content
Back to search

mcp-confluent

An open-source MCP server that enables AI assistants to interact with Confluent Cloud, Confluent Platform, and standalone Apache Kafka deployments through natural language. It provides 50+ tools…

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/confluentinc/mcp-confluent with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/confluentinc/mcp-confluent'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/confluentinc--mcp-confluent/badge.svg)](/listings/confluentinc--mcp-confluent)

HTML

<a href="/listings/confluentinc--mcp-confluent"><img src="/api/listings/confluentinc--mcp-confluent/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

> **Prerequisites:** [Node.js 22.19.0+](https://nodejs.org/). > If you want to interact with [Confluent Cloud](https://confluent.cloud/), you need to create an account first.

1. Generate a quick `config.yaml` file in your project root:

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

2. Edit the `config.yaml` file with your connection details, then:

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

See [Getting Started](#getting-started) for full setup instructions and [Configuring MCP Clients](#configuring-mcp-clients) for integration with your preferred AI tool.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 504 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Confluent MCP Server
  2. [![npm version](https://img.shields.io/npm/v/@confluentinc/mcp-confluent.svg)](https://www.npmjs.com/package/@confluentinc/mcp-confluent)
  3. [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
  4. An open-source [MCP server](https://modelcontextprotocol.io/) that enables AI assistants to interact with Confluent Cloud, Confluent Platform, and standalone Apache Kafka deployments through natural language.
  5. It provides 50+ tools across Kafka, Flink SQL, Schema Registry, Connectors, Tableflow, and more -- usable from any MCP-compatible client including Claude Desktop, Claude Code, Cursor, VS Code, Goose, and Gemini CLI.
  6. > [!TIP]
  7. > **Already a Confluent Cloud customer?**
  8. > Confluent offers a [fully managed MCP server](https://docs.confluent.io/cloud/current/ai/ai-tools/managed-mcp-server.html) with no local server to run and no dependencies to install.
  9. > It provides access to your Confluent Cloud resources with AI-powered connector diagnostics, governed by your existing RBAC permissions.
  10. > Use this open-source server if you need Confluent Platform / self-managed Kafka support, or want to customize and extend the toolset.
  11. >
  12. > **NOTE:** The open-source MCP server is a community-supported project. Confluent doesn’t provide dedicated support for it, and support is best-effort only, with no service level commitments. If you run into an issue or want to contribute, open an issue or pull request directly in this repository.
  13. ## Quick Start
  14. > **Prerequisites:** [Node.js 22.23.4+](https://nodejs.org/).
  15. > If you want to interact with [Confluent Cloud](https://confluent.cloud/), you need to create an account first.
  16. 1. Generate a quick `config.yaml` file in your project root:
  17. ```bash
  18. npx @confluentinc/mcp-confluent --init-config
  19. ```
  20. 2. Edit the `config.yaml` file with your connection details, then:
  21. ```bash
  22. npx @confluentinc/mcp-confluent --config ./config.yaml
  23. ```
  24. See [Getting Started](#getting-started) for full setup instructions and [Configuring MCP Clients](#configuring-mcp-clients) for integration with your preferred AI tool.
  25. ## Table of Contents
  26. - [Quick Start](#quick-start)
  27. - [Available Tools](#available-tools)
  28. - [Always Available](#always-available-tools)
  29. - [Confluent Cloud](#available-tools-for-confluent-cloud)
  30. - [Local deployments](#available-tools-for-local-deployments)
  31. - [Using with Confluent Platform](#using-with-confluent-platform)
  32. - [Getting Started](#getting-started)
  33. - [Configuration](#configuration)
  34. - [OAuth Authentication for Confluent Cloud](#oauth-authentication-for-confluent-cloud)
  35. - [CLI Usage](#cli-usage)
  36. - [Configuring MCP Clients](#configuring-mcp-clients)
  37. - [Telemetry](#telemetry)
  38. - [Troubleshooting](#troubleshooting)
  39. - [Contributing](#contributing)
  40. ## Available Tools
  41. Tools are auto-enabled based on which service blocks are present in your resolved configuration; see [CONFIGURATION.md](CONFIGURATION.md#tool-enablement-which-block-lights-up-what) for the full block-to-tool mapping.
  42. You can list all available tools via the CLI:
  43. ```bash
  44. npx -y @confluentinc/mcp-confluent --list-tools
  45. ```
  46. ### Always-Available Tools
  47. These tools need no service blocks or authentication — they're enabled even on a bare config, regardless of which deployment the rest of your config targets.
  48. | Category | Tools | Description |
  49. | ----------------- | -------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
  50. | **Documentation** | `search-product-docs`, `get-product-doc-page` | Search Confluent product docs and fetch full page content |
  51. | **Diagnostics** | `explain-disabled-tools`, `list-configured-connections`, `config-help`, `describe-configured-connection` | Explain why tools are absent, list configured connections and the tools enabled on each, suggest the YAML to enable a specific tool, and describe one connection's config and tool availability |
  52. ### Available Tools for Confluent Cloud
  53. These tools require endpoints and authentication against specific Confluent Cloud components.
  54. Refer to [`config.example.yaml`](config.example.yaml) for the full set of configuration variables.
  55. Categories marked with ¹ also work with [OAuth authentication](#oauth-authentication-for-confluent-cloud) — sign in via your browser instead of provisioning API keys.
  56. | Category | Tools | Description |
  57. | -------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------ |
  58. | **Kafka** ¹ | `list-topics`, `create-topics`, `delete-topics`, `produce-message`, `consume-messages`, `list-consumer-groups`, `describe-consumer-group`, `get-consumer-group-lag`, `alter-topic-config`, `get-topic-config` | Manage topics, produce/consume messages, inspect consumer groups, configure topic settings |
  59. | **Flink SQL** ¹ | `create-flink-statement`, `list-flink-statements`, `get-flink-statement-results`, `delete-flink-statements`, `get-flink-statement-exceptions`, `list-compute-pools` | Create and manage Flink SQL statements; discover Flink compute pools |
  60. | **Flink Catalog** ¹ | `list-flink-catalogs`, `list-flink-databases`, `list-flink-tables`, `describe-flink-table`, `get-flink-table-info` | Explore Flink catalogs, databases, and table schemas |
  61. | **Flink Diagnostics** ¹ | `check-flink-statement-health`, `detect-flink-statement-issues`, `get-flink-statement-profile` | Health checks, issue detection, and query profiling |
  62. | **Connectors** ¹ | `list-connectors`, `get-connector-config`, `get-connector-offsets`, `get-connector-status`, `get-connector-tasks`, `get-connector-error-summary`, `get-connector-error-recommendations`, `get-connector-logs`, `create-connector` ², `delete-connector`, `pause-connector`, `resume-connector`, `restart-connector`, `update-connector-config` | Inspect and manage Kafka Connect connectors |
  63. | **Schema Registry** ¹ | `list-schemas`, `create-schema`, `delete-schema` | List, inspect, create, and delete data schemas |
  64. | **Catalog & Tags** ¹ | `search-topics-by-tag`, `search-topics-by-name`, `create-topic-tags`, `delete-tag`, `remove-tag-from-entity`, `add-tags-to-topic`, `list-tags` | Organize and search topics using tags |
  65. | **Organizations, Environments & Clusters** ¹ | `list-organizations`, `list-environments`, `read-environment`, `list-clusters` | Discover Confluent Cloud resources |
  66. | **Tableflow** ¹ | `create-tableflow-topic`, `list-tableflow-topics`, `read-tableflow-topic`, `update-tableflow-topic`, `delete-tableflow-topic`, `list-tableflow-regions` | Manage Tableflow-enabled topics |
  67. | **Tableflow Catalog** ¹ | `create-tableflow-catalog-integration`, `list-tableflow-catalog-integrations`, `read-tableflow-catalog-integration`, `update-tableflow-catalog-integration`, `delete-tableflow-catalog-integration` | Manage Tableflow catalog integrations (e.g., AWS Glue) |
  68. | **Metrics** ¹ | `list-available-metrics`, `query-metrics` | Discover and query Confluent Cloud operational metrics |
  69. | **Billing** ¹ | `list-billing-costs` | Query billing and cost data |
  70. ¹ Also available under OAuth — see [OAuth Authentication for Confluent Cloud](#oauth-authentication-for-confluent-cloud) for setup and caveats.
  71. Categories not marked currently require a `direct` connection with static API keys; OAuth migration is in progress.
  72. ² Individual tool not available under OAuth; requires a `direct` connection with static API keys.
  73. ### Available Tools for local deployments
  74. These tools only require Kafka or Schema Registry endpoints - no Confluent Cloud API key/secret is needed.
  75. Ideal for local development with self-managed clusters, including Confluent Platform.
  76. ```yaml
  77. # minimal config.yaml for local development
  78. connections:
  79. local:
  80. type: direct
  81. kafka:
  82. bootstrap_servers: "localhost:9092"
  83. schema_registry:
  84. endpoint: "http://localhost:8081"
  85. ```
  86. Ready-to-use variants live in [`sample_configs/`](sample_configs/).
  87. | Category | Tools | Description |
  88. | ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------- |
  89. | **Kafka** | `list-topics`, `create-topics`, `delete-topics`, `produce-message`, `consume-messages`, `list-consumer-groups`, `describe-consumer-group`, `get-consumer-group-lag` | Manage topics, produce/consume messages, inspect consumer groups |
  90. | **Schema Registry** | `list-schemas`, `create-schema`, `delete-schema` | List, inspect, create, and delete data schemas |
  91. ## Using with Confluent Platform
  92. `mcp-confluent` runs against a self-managed Confluent Platform (CP) cluster the same way it runs against any local Kafka + Schema Registry deployment: point a `direct` connection at your brokers and Schema Registry.
  93. A CP connection exposes the same tools as any other local deployment — see [Available Tools for local deployments](#available-tools-for-local-deployments).
  94. The Confluent Cloud tools (Flink, Tableflow, Billing, Metrics, and the rest) require a Confluent Cloud account and stay disabled on CP.
  95. The only differences from a `localhost:9092` setup are authentication and TLS.
  96. ### Sample YAML config
  97. [`sample_configs/confluent-platform.yaml`](sample_configs/confluent-platform.yaml) is a copy-pasteable starter.
  98. It assumes PLAIN over SASL_SSL for Kafka and HTTP Basic Auth for Schema Registry.
  99. Customize the broker and Schema Registry URLs, and inject credentials via the `${KAFKA_API_KEY}` / `${KAFKA_API_SECRET}` / `${SCHEMA_REGISTRY_API_KEY}` / `${SCHEMA_REGISTRY_API_SECRET}` environment variables.
  100. If your cluster uses SCRAM or another SASL mechanism, override `security.protocol` and `sasl.mechanisms` through the `kafka.extra_properties` map in that file.
  101. ### TLS trust (internal CAs)
  102. CP clusters frequently sit behind an internal CA.
  103. If you see TLS handshake failures against the broker or Schema Registry, point Node at your CA bundle when starting the server:
  104. ```bash
  105. NODE_EXTRA_CA_CERTS=/path/to/internal-ca.pem pnpm run start -- --config path/to/config.yaml
  106. ```
  107. ### End-to-end smoke test
  108. A docker-compose stack ([`docker-compose.cp-test.yml`](docker-compose.cp-test.yml)) brings up a local CP Kafka (KRaft, SASL_PLAINTEXT/PLAIN) plus an unauthenticated Schema Registry.
  109. The matching integration tests are tagged `@cp` and live next to their handlers as `*.cp.integration.test.ts`:
  110. ```bash
  111. docker compose -f docker-compose.cp-test.yml up -d
  112. # Wait ~30s for Kafka + SR to become ready, then:
  113. CP_KAFKA_USERNAME=mcp CP_KAFKA_PASSWORD=mcp-secret \
  114. pnpm run test:integration --tags-filter=@cp
  115. docker compose -f docker-compose.cp-test.yml down -v
  116. ```
  117. The tests skip cleanly when those env vars are unset, so `pnpm run test:unit` and a default `pnpm run test:integration` against your real Confluent Cloud account are unaffected if you don't have the docker stack running.
  118. ## Getting Started
  119. ### Prerequisites
  120. - **Node.js 22.23.4 or later** -- we recommend using [NVM](https://github.com/nvm-sh/nvm) to manage versions:
  121. ```bash
  122. nvm install 22
  123. nvm use 22
  124. ```
  125. - **[pnpm](https://pnpm.io/installation)** -- only needed to build from source (the `npx` quick start above does not require it).
  126. On macOS the simplest install is Homebrew; `npm` works cross-platform:
  127. ```bash
  128. brew install pnpm # macOS
  129. # or, cross-platform:
  130. npm install -g pnpm
  131. ```
  132. See pnpm's [installation guide](https://pnpm.io/installation) for other options.
  133. The exact pnpm version is pinned in the `packageManager` field of `package.json`, and pnpm automatically runs that pinned version (via its built-in package-manager version management), so a recent pnpm install is all you need -- no separate Corepack setup required.
  134. - A local environment with Kafka or Schema Registry running, or a **Confluent Cloud** account with appropriate API keys or login credentials if [using OAuth to authenticate](#oauth-authentication-for-confluent-cloud).
  135. ### General Setup Steps
  136. This MCP server is designed to be used with various MCP clients, such as Claude Desktop, Copilot, or Goose CLI/Desktop.
  137. The specific configuration and interaction will depend on the client you are using.
  138. The MCP server can authenticate to Confluent Cloud via **OAuth (PKCE)** in addition to static API keys defined in the YAML config.
  139. See [OAuth Authentication For Confluent Cloud](#oauth-authentication-for-confluent-cloud) for more details.
  140. The general steps to configure (if not using OAuth) and run this MCP are:
  141. 1. **Create a configuration file:** Copy the provided [`config.yaml` example](https://github.com/confluentinc/mcp-confluent/blob/main/config.example.yaml) file to the root of your project.
  142. You can use the CLI to bootstrap one in your current directory — no git checkout required:
  143. ```bash
  144. npx @confluentinc/mcp-confluent --init-config
  145. ```
  146. 2. **Populate the file:** Fill in the necessary values for your Confluent Cloud environment.
  147. See [CONFIGURATION.md](CONFIGURATION.md) for the full reference; only fill in the service blocks you need (each one enables a group of tools).
  148. 3. **Start the Server:** You can run the MCP server in one of two ways:
  149. - **From source:** Follow the instructions in the [Contributing Guide](CONTRIBUTING.md) to build and run the server from source.
  150. This typically involves:
  151. - Installing dependencies (`pnpm install`)
  152. - Building the project (`pnpm run build` or `pnpm run dev`)
  153. - **With npx:** You can start the server directly using npx, no build required:
  154. ```bash
  155. npx @confluentinc/mcp-confluent --config /path/to/myconfig.yaml
  156. ```
  157. 4. **Configure your MCP Client:** Each client (e.g., Claude, Goose) will have its own way of specifying the MCP server's address and any required credentials.
  158. You'll need to [configure your client](#configuring-mcp-clients) to connect to the address where this server is running (likely `localhost` with a specific port).
  159. The port the server runs on is set via `server.http.port` in `config.yaml`.
  160. 5. **Start your MCP Client:** Once your client is configured to connect to the MCP server, you can start your MCP client and on startup it will stand up an instance of this MCP server locally.
  161. This instance will be responsible for managing data schemas and interacting with resources on your behalf.
  162. 6. **Interact with your resources through the Client:** Once the client is connected and configured, you can use the client's interface to interact with Confluent Cloud or local resources.
  163. The client will send requests to this MCP server, which will then interact with the available connections on your behalf.
  164. ## Configuration
  165. The full configuration reference — YAML schema, every service block, env-var interpolation, OAuth and HTTP/SSE auth setup, the (deprecated) legacy env-var table, and tool-to-block mapping — lives in [CONFIGURATION.md](CONFIGURATION.md).
  166. > **Compatibility note.** This release ships full parity between YAML (`-c config.yaml`) and the legacy env-var path (`-e config.env`) for a single connection.
  167. > The env-var-only path will emit a startup warning in a near-future release and be removed a release or two later.
  168. > Defining multiple connections (or none) is YAML-only — the env-var path can express only a single connection.
  169. > See [CONFIGURATION.md → Two paths, one configuration](CONFIGURATION.md#two-paths-one-configuration) and [CONFIGURATION.md → Multiple connections (and zero connections)](CONFIGURATION.md#multiple-connections-and-zero-connections).
  170. ### Prerequisites & setup for Tableflow commands
  171. Tableflow tools interact with cloud storage (e.g. AWS S3) and a metadata catalog (e.g. AWS Glue) on your behalf via the Flink runtime in Confluent Cloud.
  172. The Flink runtime needs IAM permissions on your cloud account, and those have to be granted and linked into Confluent Cloud before any Tableflow tool will succeed.
  173. Follow the **[Tableflow quick start with custom storage & Glue](https://docs.confluent.io/cloud/current/topics/tableflow/get-started/quick-start-custom-storage-glue.html)** to set up the roles, policies, and provider integrations.
  174. Skipping this step leads to authorization errors when mcp-confluent tries to provision or manage Tableflow-enabled tables.
  175. ## OAuth Authentication for Confluent Cloud
  176. The MCP server can authenticate to Confluent Cloud via **OAuth (PKCE)** instead of static API keys.
  177. On the first tool call that needs Confluent access, the server opens your browser to the Confluent Cloud sign-in page; subsequent tool calls reuse the resulting session.
  178. No API keys to provision.
  179. ### Setup
  180. ```bash
  181. npx @confluentinc/mcp-confluent --init-oauth-config
  182. # edit ./config.yaml if needed, then:
  183. npx @confluentinc/mcp-confluent --config ./config.yaml
  184. ```
  185. `--init-oauth-config` drops a starter [`config.oauth.example.yaml`](config.oauth.example.yaml) into `./config.yaml`.
  186. The whole file is essentially:
  187. ```yaml
  188. connections:
  189. ccloud-oauth:
  190. type: oauth
  191. ```
  192. See [CONFIGURATION.md → Authentication modes](CONFIGURATION.md#authentication-modes) for the full schema and ergonomics.
  193. The ¹-marked categories in [Available Tools for Confluent Cloud](#available-tools-for-confluent-cloud) work under OAuth today; everything else still needs a `direct` connection with static API keys.
  194. ## CLI Usage
  195. The MCP server provides a flexible command line interface (CLI) for advanced control.
  196. The CLI lets you pick the config file, transports, and fine-tune which tools are enabled or blocked.
  197. ### Basic Usage
  198. You can view all CLI options and help with:
  199. ```bash
  200. npx @confluentinc/mcp-confluent --help
  201. ```
  202. <details>
  203. <summary>Show output</summary>
  204. ```bash
  205. Usage: mcp-confluent [options]
  206. Confluent MCP Server - Model Context Protocol implementation for Confluent Cloud
  207. Options:
  208. -V, --version output the version number
  209. -e, --env-file <path> Load environment variables from file
  210. -k, --kafka-config-file <file> Path to a properties file for configuring kafka clients
  211. -t, --transport <types> Transport types (comma-separated list) (choices: "http", "sse", "stdio", default: "stdio")
  212. --allow-tools <tools> Comma-separated list of tool names to allow. If provided, takes precedence over --allow-tools-file. Allow-list is applied before block-list.
  213. --block-tools <tools> Comma-separated list of tool names to block. If provided, takes precedence over --block-tools-file. Block-list is applied after allow-list.
  214. --allow-tools-file <file> File with tool names to allow (one per line). Used only if --allow-tools is not provided. Allow-list is applied before block-list.
  215. --block-tools-file <file> File with tool names to block (one per line). Used only if --block-tools is not provided. Block-list is applied after allow-list.
  216. --list-tools Print the final set of enabled tool names (with descriptions) after allow/block filtering and exit. Does not start the server.
  217. --disable-auth Disable authentication for HTTP/SSE transports. WARNING: Only use in development environments.
  218. --allowed-hosts <hosts> Comma-separated list of allowed Host header values for DNS rebinding protection.
  219. --generate-key Generate a secure API key for MCP_API_KEY and print it to stdout, then exit.
  220. -h, --help display help for command
  221. ```
  222. </details>
  223. ### Example: Deploy using all transports
  224. ```bash
  225. npx @confluentinc/mcp-confluent -c config.yaml --transport http,sse,stdio
  226. ```
  227. <details>
  228. <summary>Show output</summary>
  229. ```json
  230. ...
  231. {"level":"info","time":"2025-05-14T17:03:02.883Z","pid":47959,"hostname":"G9PW1FJH64","name":"mcp-confluent","msg":"Starting transports: http, sse, stdio"}
  232. {"level":"info","time":"2025-05-14T17:03:02.971Z","pid":47959,"hostname":"G9PW1FJH64","name":"mcp-confluent","msg":"HTTP transport routes registered"}
  233. {"level":"info","time":"2025-05-14T17:03:02.972Z","pid":47959,"hostname":"G9PW1FJH64","name":"mcp-confluent","msg":"SSE transport routes registered"}
  234. {"level":"info","time":"2025-05-14T17:03:02.972Z","pid":47959,"hostname":"G9PW1FJH64","name":"mcp-confluent","msg":"STDIO transport connected"}
  235. {"level":"info","time":"2025-05-14T17:03:03.012Z","pid":47959,"hostname":"G9PW1FJH64","name":"mcp-confluent","msg":"Server listening at http://[::1]:3000"}
  236. {"level":"info","time":"2025-05-14T17:03:03.013Z","pid":47959,"hostname":"G9PW1FJH64","name":"mcp-confluent","msg":"Server listening at http://127.0.0.1:3000"}
  237. {"level":"info","time":"2025-05-14T17:03:03.013Z","pid":47959,"hostname":"G9PW1FJH64","name":"mcp-confluent","msg":"All transports started successfully"}
  238. ```
  239. </details>
  240. ### Example: Allow Only Specific Tools
  241. ```bash
  242. npx @confluentinc/mcp-confluent -c config.yaml --allow-tools produce-message,consume-messages
  243. ```
  244. Only the specified tools will be enabled; all others will be disabled.
  245. ### Example: Block Certain Tools
  246. ```bash
  247. npx @confluentinc/mcp-confluent -c config.yaml --block-tools produce-message,consume-messages
  248. ```
  249. All tools except the specified ones will be enabled.
  250. ### Example: Use Tool Lists from Files
  251. You can also maintain allow/block lists in files (one tool name per line):
  252. ```bash
  253. npx -y @confluentinc/mcp-confluent -c config.yaml --allow-tools-file allow.txt --block-tools-file block.txt
  254. ```
  255. ### Example: List All Available Tools
  256. ```bash
  257. npx -y @confluentinc/mcp-confluent --list-tools
  258. ```
  259. <details>
  260. <summary>Show output</summary>
  261. ```text
  262. billing:
  263. list-billing-costs: Retrieve billing cost data for a Confluent Cloud organization within a specified date range with pagination support
  264. catalog:
  265. add-tags-to-topic: Assign existing tags to Kafka topics in Confluent Cloud.
  266. create-topic-tags: Create new tag definitions in Confluent Cloud.
  267. delete-tag: Delete a tag definition from Confluent Cloud.
  268. list-tags: Retrieve all tags with definitions from Confluent Cloud Schema Registry.
  269. remove-tag-from-entity: Remove tag from an entity in Confluent Cloud.
  270. search-topics-by-name: List all topics in the Kafka cluster matching the specified name.
  271. search-topics-by-tag: List all topics in the Kafka cluster with the specified tag.
  272. confluent-cloud:
  273. list-clusters: Get all clusters in the Confluent Cloud environment
  274. list-environments: Get all environments in Confluent Cloud with pagination support
  275. list-organizations: List Confluent Cloud organizations the current credentials can see. Paginated; if the response includes a nextPageTok...
  276. read-environment: Get details of a specific environment by ID
  277. connect:
  278. create-connector: Create a new connector. Returns the new connector information if successful.
  279. delete-connector: Delete an existing connector. Returns success message if deletion was successful.
  280. get-connector-config: Retrieve the full configuration map for a connector. Returns the flat config object the connector was created/updated...
  281. get-connector-error-recommendations: Get suggested remediation steps for a connector that has failed or is in an error state. Returns a one-liner when no recommendations are available.
  282. get-connector-error-summary: Summarize a connector's current errors. Projects Confluent Cloud's /status diagnostics into a compact, agent-friendly form. Returns a one-liner when the connector is healthy.
  283. get-connector-logs: Retrieve recent log entries for a Confluent Cloud connector from the Cloud logging API. Defaults to the last hour of ERROR-level entries. Paginated via nextPageToken.
  284. get-connector-offsets: Retrieve current offsets for a connector's tasks. Useful for detecting lag, stalled tasks, or assisting recovery.
  285. get-connector-status: Get the current state of a connector and its tasks (RUNNING, FAILED, PAUSED, UNASSIGNED) including failure traces if ...
  286. get-connector-tasks: List the tasks of a connector along with their configurations.
  287. list-connectors: Retrieve a list of "names" of the active connectors. You can then make a read request for a specific connector by name.
  288. pause-connector: Pause a running connector and its tasks. Idempotent.
  289. restart-connector: Restart a connector and its tasks. Asynchronous; the connector will not transition state synchronously.
  290. resume-connector: Resume a paused connector and its tasks. Idempotent.
  291. update-connector-config: Update the configuration of an existing connector. Full-replace: omitted keys are removed and the connector is reconf...
  292. docs:
  293. get-product-doc-page: Fetch the full markdown content of a Confluent product documentation page. Accepts URLs under https://docs.confluent....
  294. search-product-docs: Search Confluent product documentation (docs.confluent.io, developer.confluent.io, support.confluent.io) by keyword.
  295. flink:
  296. check-flink-statement-health: Perform an aggregate health check for a Flink SQL statement. Returns status (healthy/warning/critical), current phase...
  297. create-flink-statement: Make a request to create a statement.
  298. delete-flink-statements: Make a request to delete a statement.
  299. describe-flink-table: Get full schema details for a Flink table via INFORMATION_SCHEMA.COLUMNS. Returns column names, data types (including...
  300. detect-flink-statement-issues: Detect issues for a Flink SQL statement by analyzing status, exceptions, and performance metrics. Identifies problems...
  301. get-flink-statement-exceptions: Retrieve the 10 most recent exceptions for a Flink SQL statement. Useful for diagnosing failed or failing statements.
  302. get-flink-statement-profile: Get Query Profiler data for a Flink SQL statement. Returns the task graph with human-readable task/operator names, pe...
  303. get-flink-statement-results: Fetch the result rows produced by a Flink SQL statement.
  304. get-flink-table-info: Get table metadata via INFORMATION_SCHEMA.TABLES. Returns watermark configuration, distribution info, and table type.
  305. list-compute-pools: Get the Flink compute pools in the Confluent Cloud environment. Paginated; if the response includes a nextPageToken, pas...
  306. list-flink-catalogs: List all catalogs available in the Flink environment via INFORMATION_SCHEMA.CATALOGS.
  307. list-flink-databases: List all databases (schemas) in a Flink catalog via INFORMATION_SCHEMA.SCHEMATA. Returns catalog and database names.
  308. list-flink-statements: Retrieve a sorted, filtered, paginated list of all statements.
  309. list-flink-tables: List all tables in a Flink database via INFORMATION_SCHEMA.TABLES. Returns table names and types.
  310. kafka:
  311. alter-topic-config: Alter topic configuration in Confluent Cloud.
  312. consume-messages: Consume messages from Kafka topics. Optionally restrict to a partition, start from an offset, timestamp, earliest, la...
  313. create-topics: Create one or more Kafka topics with an optional partition count and replication factor.
  314. delete-topics: Delete the topic with the given names.
  315. describe-consumer-group: Describe a single consumer group on a Kafka cluster. Returns the group's state, type, protocol, partition assignor, c...
  316. get-consumer-group-lag: Compute live offset lag for a single Kafka consumer group. Returns per-(topic, partition) {committedOffset, highWater...
  317. get-partition-offsets: Return per-partition low/high watermarks and message counts for a Kafka topic. Use this to size a backfill, measure l...
  318. get-topic-config: Retrieve configuration details for a specific Kafka topic.
  319. list-consumer-groups: List consumer groups on a Kafka cluster — wraps the broker's listGroups admin call. Optional filters narrow the resul...
  320. list-topics: List all topics in the Kafka cluster.
  321. produce-message: Produce records to a Kafka topic. Supports Confluent Schema Registry serialization (AVRO, JSON, PROTOBUF) for both ke...
  322. mcp-server-diagnostics:
  323. 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 cr...
  324. explain-disabled-tools: Call when the user asks why a tool is missing or unavailable (e.g., "why can't I list Kafka topics?", "where are the ...
  325. list-configured-connections: List every configured connection and the connection-routable tools you can invoke against each. The connection id (th...
  326. metrics:
  327. list-available-metrics: List available Confluent Cloud metrics and their filter fields from the Telemetry API. Use this tool BEFORE query-met...
  328. query-metrics: Query Confluent Cloud metrics from the Telemetry API. IMPORTANT: Use the list-available-metrics tool first to discove...
  329. schema-registry:
  330. create-schema: Register a new schema (or a new version of an existing schema) under a subject in the Schema Registry.
  331. delete-schema: Delete a schema subject or a specific version from the Schema Registry. If version is omitted, all versions of the su...
  332. list-schemas: List all schemas in the Schema Registry.
  333. tableflow:
  334. create-tableflow-catalog-integration: Make a request to create a catalog integration.
  335. create-tableflow-topic: Make a request to create a tableflow topic.
  336. delete-tableflow-catalog-integration: Make a request to delete a tableflow catalog integration.
  337. delete-tableflow-topic: Make a request to delete a tableflow topic.
  338. list-tableflow-catalog-integrations: Retrieve a sorted, filtered, paginated list of all catalog integrations.
  339. list-tableflow-regions: Retrieve a sorted, filtered, paginated list of all tableflow regions.
  340. list-tableflow-topics: Retrieve a sorted, filtered, paginated list of all tableflow topics.
  341. read-tableflow-catalog-integration: Make a request to read a catalog integration.
  342. read-tableflow-topic: Make a request to read a tableflow topic.
  343. update-tableflow-catalog-integration: Make a request to update a catalog integration.
  344. update-tableflow-topic: Make a request to update a tableflow topic.
  345. ```
  346. </details>
  347. > **Tip:** The allow-list is applied before the block-list.
  348. > If neither is provided, all tools are enabled by default.
  349. ## Configuring MCP Clients
  350. Please refer to the following guides for step-by-step instructions on setting up and using this MCP server with your preferred client:
  351. - [Claude Code](docs/configuring-claude-code.md)
  352. - [Claude Desktop](docs/configuring-claude-desktop.md)
  353. - [Cursor](docs/configuring-cursor.md)
  354. - [Gemini CLI](docs/configuring-gemini-cli.md)
  355. - [Goose CLI](docs/configuring-goose-cli.md)
  356. - [IBM Bob](docs/configuring-ibm-bob.md)
  357. - [VS Code](docs/configuring-vs-code.md)
  358. - [Windsurf](docs/configuring-windsurf.md)
  359. ## Telemetry
  360. This MCP server collects usage data and reports server-side runtime errors (via [Sentry](https://sentry.io)) to help make improvements.
  361. You can opt out of both by setting `DO_NOT_TRACK=true` in your environment (or `server.do_not_track: true` in YAML).
  362. See [telemetry.md](telemetry.md) for full details on what is collected and what is never sent.
  363. ## Troubleshooting
  364. **"Node.js version not supported"** -- This project requires Node.js 22.23.4 or later.
  365. Check your version with `node -v` and upgrade if needed.
  366. **Tools not appearing** -- Each tool requires specific service blocks in your `config.yaml`.
  367. Run `--list-tools` to see which tools are active, or invoke the `explain-disabled-tools` MCP tool from your client for a per-tool reason.
  368. The block-to-tool mapping lives in [CONFIGURATION.md](CONFIGURATION.md#tool-enablement-which-block-lights-up-what).
  369. **Authentication errors on HTTP/SSE** -- Generate an API key with `npx @confluentinc/mcp-confluent --generate-key` and add it to your `config.yaml` under `server.auth.api_key`.
  370. See [CONFIGURATION.md → HTTP/SSE transport security](CONFIGURATION.md#httpsse-transport-security).
  371. **Connection refused / port conflicts** -- The default HTTP port is 8080.
  372. Set `server.http.port` in your `config.yaml` to change it.
  373. **Tableflow authorization errors** -- Tableflow tools require specific IAM permissions in your cloud environment.
  374. See [Prerequisites & setup for Tableflow commands](#prerequisites--setup-for-tableflow-commands).
  375. ## Contributing
  376. Bug reports and feedback is appreciated in the form of Github Issues.
  377. For guidelines on contributing please see [CONTRIBUTING.md](CONTRIBUTING.md)
  378. ### Pre-release testing
  379. To run the MCP server against a pre-release version for beta testing or early feedback, download the release tarball file to a local directory.
  380. Then, when running any of the `npx` commands above, replace `@confluentinc/mcp-confluent` with the path to that tarball, e.g. `npx @~path/to/my/tarball --list-tools`

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.