| FMRS | 54 / 100 · D | 79 / 100 · B | 74 / 100 · B |
|---|
| Reliability | 6 / 20 | 12 / 20 | 13 / 20 |
|---|
| Security and permissions | 9 / 20 | 18 / 20 | 13 / 20 |
|---|
| Maintenance | 12 / 20 | 17 / 20 | 17 / 20 |
|---|
| Documentation | 14 / 20 | 17 / 20 | 16 / 20 |
|---|
| Setup experience | 13 / 20 | 15 / 20 | 15 / 20 |
|---|
| Best for | - AI assistants interacting with Confluent Cloud or Kafka
- Development environments using Confluent Platform or local Kafka
- Teams needing a unified toolset for Kafka, Flink, Schema Registry
| - Teams already using ClickHouse who want AI assistants to access data directly.
- Scenarios requiring fast, read-only data queries and schema exploration.
| - Teams that want precise control over which database operations an AI can perform, rather than open arbitrary SQL execution
- Scenarios needing a unified MCP setup across multiple database engines
|
|---|
| Not for | - Kafka users outside the Confluent ecosystem (only subset of tools available)
- Users wanting a fully managed MCP server (consider Confluent's managed service)
- Users requiring dedicated support (community support is best-effort only)
| - Scenarios requiring write access to the database without explicit opt-in.
- Production environments with stringent security requirements that avoid default permission settings.
| - Lightweight cases that just want to run a few ad-hoc SQL queries without maintaining a tools.yaml config (a simpler single-database MCP may be a better fit)
|
|---|
| Required permissions | - Access Kafka topics, consumer groups, and configurations
- Execute Flink SQL statements and read results
- Manage schemas in Schema Registry
- Manage connectors and Tableflow topics
- Read Confluent Cloud metrics and billing data
| - Requires read-only access to ClickHouse database (default).
- Optional: write access via CLICKHOUSE_ALLOW_WRITE_ACCESS.
- Optional: destructive operations via CLICKHOUSE_ALLOW_DROP.
| - Database credentials (username/password/connection string) are supplied via env vars or config
- A tool's actual permission is whatever SQL statement is defined in tools.yaml — designed for least privilege, but misconfiguration can still over-expose access
|
|---|
| Risks and side effects | - Destructive operations (e.g., delete topics, delete schemas) must be authorized carefully
- OAuth credentials might be exposed if config files are not protected
- HTTP/SSE transports without API key may be vulnerable to unauthorized access
- Tableflow tools require cloud IAM permissions; misconfiguration may cause authorization errors
| - If write access is enabled, AI might make unintended modifications.
- If DROP access is enabled, data deletion could occur accidentally.
- Credentials may be exposed via environment variables.
| - If tools.yaml defines SQL statements that allow unconstrained writes or deletes, the AI could accidentally modify data
- The prebuilt toolsets (--prebuilt) favor convenience and may expose broader query capability than a specific business actually needs — use a custom tools.yaml in production
|
|---|
| Supported clients | Claude Desktop, Claude Code, Cursor, VS Code, Goose, Gemini CLI | Claude Desktop | Claude Code, Gemini CLI, Zed, Antigravity |
|---|
| Tools | 73 | 4 | 0 |
|---|