All servers / Infrastructure / Confluent MCP server
Confluent MCP server
Confluent MCP Server
Tested by ConnectATDScore 90 out of 100. Tested 2026-11-19 on package version 1.6.1. Package: @confluentinc/mcp-confluent · source
Score breakdown
| Runs | 18 / 20 | |
|---|---|---|
| Tool descriptions | 20 / 20 | |
| Package safety | 20 / 20 | |
| Maintenance | 20 / 20 | |
| Adoption | 12 / 20 |
What we saw
- Starts and answers the MCP handshake: yes (25.8 seconds including download)
- Tools offered: 6
- Last published: 2026-10-26
- Weekly downloads (npm): 1,343
- License: MIT · Direct dependencies: 22
Want this server set up for your team?
ConnectATD builds AI automation and wires up MCP servers like this one. Tell us what you are trying to do.
Talk to ConnectATDTools and how they are described
Agents choose tools from these descriptions. Under each name you can see how many of its parameters are explained.
search-product-docs2 of 2 parameters describedSearch Confluent product documentation (docs.confluent.io, developer.confluent.io, support.confluent.io) by keyword.
get-product-doc-page1 of 1 parameter describedFetch the full markdown content of a Confluent product documentation page. Accepts URLs under https://docs.confluent.io/, https://developer.confluent.io/, or https://support.confluent.io/. Use this after search-product-docs to read a result's full content.
explain-disabled-tools1 of 1 parameter describedCall when the user asks why a tool is missing or unavailable (e.g., "why can't I list Kafka topics?", "where are the Flink tools?"). Returns disabled tools organized per connection — each connection's gaps bucketed by the config piece each tool is waiting on, so you can tell the user the exact YAML block or field to add (and, with more than one connection, which connection needs it). Pass group_by="category" to bucket each connection's gaps by functional area (kafka, flink, schema-registry, …) instead of by missing config piece. Prefer this over guessing about credentials, network, or auth.
list-configured-connectionsno parametersList every configured connection and the connection-routable tools you can invoke against each. The connection id (the map key) is the value to pass as the `connectionId` argument on tools that ask for one. Each connection also reports `readOnly`: when true, the connection is marked read-only and exposes only non-mutating tools. Connection-agnostic tools (e.g. docs and diagnostics that take no `connectionId`) are always available and appear in `tools/list`, not here. Call this when a tool offers a choice of connections, or to discover which connection supports the capability you need.
config-help1 of 1 parameter describedCall 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.
describe-configured-connection1 of 1 parameter describedDescribe one configured connection by id: its non-secret config (type, endpoints, resource ids — never credentials), whether it is read-only, the tools you can invoke against it, and, for tools that are unavailable on it, the config gap or policy keeping each one off. Pass the connection id from 'list-configured-connections'. Call this to learn what a specific connection supports before routing a tool call to it.
Tested in a sandbox with an empty environment: no API keys, a throwaway folder, nothing from a real account. A passing test shows the server runs and responds. It is not a security audit.