mcp-server-kafka
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_KAFKA_BOOTSTRAP_SERVERS | Yes | The Kafka bootstrap servers (e.g. localhost:9092) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| kafka_cluster_infoA | 获取 Kafka 集群整体元数据与 Broker 节点列表（包含 Cluster ID、控制器与节点地址） |
| kafka_list_topicsB | 列出 Kafka 集群中的主题清单（支持按名称模式过滤并默认排除内部系统主题） |
| kafka_describe_topicB | 查询指定 Kafka 主题的详细拓扑（分区分布、Leader 节点、ISR 同步副本与配置） |
| kafka_create_topicB | 在 Kafka 集群中创建新主题（支持指定分区数与副本因子；只读模式下不可用） |
| kafka_delete_topicA | 从 Kafka 集群中删除主题（高危破坏操作，必须传入 confirm=True 显式确认） |
| kafka_produce_messageB | 向指定 Kafka 主题发送消息（支持 Key、JSON/文本载荷与 Headers；只读模式下不可用） |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Kafka 集群拓扑摘要 | 以只读上下文形式输出当前 Kafka 集群整体元数据与 Broker 运行节点摘要 |
TDQS
Scored across 6 tools
Each tool targets a distinct Kafka resource and action: cluster metadata, topic listing, topic description, topic creation, topic deletion, and message production. There is no functional overlap or ambiguity between any pair.
All tools share the kafka_ prefix and five use a consistent verb_noun pattern (list_topics, describe_topic, create_topic, delete_topic, produce_message). The lone outlier is kafka_cluster_info, which uses a noun phrase rather than a verb, but this is a minor deviation.
Six tools is well-scoped for Kafka administration and message production, with each tool earning its place and no redundant operations. The count is neither bloated nor too thin for the apparent domain.
The set covers cluster info, topic lifecycle (create/delete/list/describe), and producing messages, but lacks any consume/read-message tool, which is a fundamental Kafka operation. Consumer group and offset management are also absent, creating a significant gap that would cause agent failures for read-oriented tasks.