Skip to main content
Glama
mcp-timeplus

mcp-timeplus

by timeplus-io

Timeplus MCP 服务器

PyPI - 版本

Timeplus 的 MCP 服务器。

特征

提示

  • generate_sql为 LLM 提供更多关于如何通过 SQL 查询 Timeplus 的知识

工具

  • run_sql

    • 在您的 Timeplus 集群上执行 SQL 查询。

    • 输入: sql (字符串):要执行的 SQL 查询。

    • 默认情况下,所有 Timeplus 查询都以readonly = 1运行,以确保其安全。如果要运行 DDL 或 DML 查询,可以将环境变量TIMEPLUS_READ_ONLY设置为false 。

  • list_databases

    • 列出 Timeplus 集群上的所有数据库。

  • list_tables

    • 列出数据库中的所有表。

    • 输入: database (字符串):数据库的名称。

  • list_kafka_topics

    • 列出 Kafka 集群中的所有主题

  • explore_kafka_topic

    • 显示 Kafka 主题中的一些消息

    • 输入: topic (字符串):主题的名称。message_count(int):要显示的message_count数,默认为 1。

  • create_kafka_stream

    • 在 Timeplus 中设置流式 ETL 以在本地保存 Kafka 消息

    • 输入: topic (字符串):主题的名称。

  • connect_to_apache_iceberg

    • 连接到基于 Apache Iceberg 的数据库。目前此功能仅支持 Timeplus Enterprise,计划很快支持 Timeplus Proton。

    • 输入: iceberg_db (字符串):Iceberg 数据库的名称aws_account_id (整数):AWS 账户 ID(12 位数字) s3_bucket (字符串):S3 存储桶名称。aws_region( aws_region ):AWS 区域,默认为“us-west-2”。is_s3_table_bucket(布尔值):S3 is_s3_table_bucket桶是否为 S3 表存储桶,默认为 False。

Related MCP server: KafkaIQ

配置

首先,请确保您已安装uv可执行文件。如果没有,您可以按照此处的说明进行安装。

  1. 打开位于以下位置的 Claude Desktop 配置文件:

    • 在 macOS 上: ~/Library/Application Support/Claude/claude_desktop_config.json

    • 在 Windows 上: %APPDATA%/Claude/claude_desktop_config.json

  2. 添加以下内容:

{
  "mcpServers": {
    "mcp-timeplus": {
      "command": "uvx",
      "args": ["mcp-timeplus"],
      "env": {
        "TIMEPLUS_HOST": "<timeplus-host>",
        "TIMEPLUS_PORT": "<timeplus-port>",
        "TIMEPLUS_USER": "<timeplus-user>",
        "TIMEPLUS_PASSWORD": "<timeplus-password>",
        "TIMEPLUS_SECURE": "false",
        "TIMEPLUS_VERIFY": "true",
        "TIMEPLUS_CONNECT_TIMEOUT": "30",
        "TIMEPLUS_SEND_RECEIVE_TIMEOUT": "30",
        "TIMEPLUS_READ_ONLY": "false",
        "TIMEPLUS_KAFKA_CONFIG": "{\"bootstrap.servers\":\"a.aivencloud.com:28864\", \"sasl.mechanism\":\"SCRAM-SHA-256\",\"sasl.username\":\"avnadmin\", \"sasl.password\":\"thePassword\",\"security.protocol\":\"SASL_SSL\",\"enable.ssl.certificate.verification\":\"false\"}"
      }
    }
  }
}

更新环境变量以指向您自己的 Timeplus 服务。

  1. 重新启动 Claude Desktop 以应用更改。

您还可以尝试将此 MCP 服务器与其他 MCP 客户端(例如5ire)一起使用。

发展

  1. 在test-services目录中运行docker compose up -d启动 Timeplus Proton 服务器。你也可以通过curl https://install.timeplus.com/oss | sh下载,然后使用./proton server启动。

  2. 将以下变量添加到存储库根目录中的.env文件中。

TIMEPLUS_HOST=localhost
TIMEPLUS_PORT=8123
TIMEPLUS_USER=default
TIMEPLUS_PASSWORD=
TIMEPLUS_SECURE=false
TIMEPLUS_VERIFY=true
TIMEPLUS_CONNECT_TIMEOUT=30
TIMEPLUS_SEND_RECEIVE_TIMEOUT=30
TIMEPLUS_READ_ONLY=false
TIMEPLUS_KAFKA_CONFIG={"bootstrap.servers":"a.aivencloud.com:28864", "sasl.mechanism":"SCRAM-SHA-256","sasl.username":"avnadmin", "sasl.password":"thePassword","security.protocol":"SASL_SSL","enable.ssl.certificate.verification":"false"}
  1. 运行uv sync安装依赖项。然后执行source .venv/bin/activate 。

  2. 为了方便测试,您可以运行mcp dev mcp_timeplus/mcp_server.py来启动 MCP 服务器。点击“连接”按钮将 UI 连接到 MCP 服务器,然后切换到“工具”选项卡运行可用的工具。

  3. 要构建 Docker 镜像,请运行docker build -t mcp_timeplus . 。

环境变量

以下环境变量用于配置 Timeplus 连接:

必需变量

  • TIMEPLUS_HOST :您的 Timeplus 服务器的主机名

  • TIMEPLUS_USER :用于身份验证的用户名

  • TIMEPLUS_PASSWORD :身份验证的密码

可选变量

  • TIMEPLUS_PORT :Timeplus 服务器的端口号

    • 默认值:如果启用 HTTPS, 8443 ;如果禁用, 8123

    • 通常不需要设置,除非使用非标准端口

  • TIMEPLUS_SECURE :启用/禁用 HTTPS 连接

    • 默认值: "false"

    • 设置为"true"以实现安全连接

  • TIMEPLUS_VERIFY :启用/禁用 SSL 证书验证

    • 默认值: "true"

    • 设置为"false"以禁用证书验证(不建议用于生产)

  • TIMEPLUS_CONNECT_TIMEOUT :连接超时(秒)

    • 默认值: "30"

    • 如果遇到连接超时,请增加此值

  • TIMEPLUS_SEND_RECEIVE_TIMEOUT :发送/接收超时(秒)

    • 默认值: "300"

    • 对于长时间运行的查询,请增加此值

  • TIMEPLUS_DATABASE :默认使用的数据库

    • 默认值:无(使用服务器默认值)

    • 将其设置为自动连接到特定数据库

  • TIMEPLUS_READ_ONLY :启用/禁用只读模式

    • 默认值: "true"

    • 设置为"false"以启用 DDL/DML

  • TIMEPLUS_KAFKA_CONFIG :Kafka 配置的 JSON 字符串。请参考librdkafka 配置或以上述示例为参考。

Available Tools

7 tools
connect_to_apache_icebergC

Create a Timeplus database in iceberg type to connect to Iceberg

Inputs: iceberg_db (required), aws_account_id (required), s3_bucket (required), aws_region, +1 more.

create_kafka_streamD

Inputs: topic (required).

explore_kafka_topicD

Inputs: topic (required), message_count.

list_databasesA

List available Timeplus databases

Inputs: no named parameters.

list_kafka_topicsD

Inputs: no named parameters.

list_tablesC

List available tables/streams in the given database

Inputs: database, like.

run_sqlC

Run a query in a Timeplus database

Inputs: query (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.4/5.0

    Scored across 7 tools

    Disambiguation3/5

    Most tools target distinct actions: listing databases, listing tables, running SQL, and connecting Iceberg are clearly separate. However, list_kafka_topics and explore_kafka_topic have overlapping territory around Kafka topics, and create_kafka_stream is adjacent to them; the empty descriptions worsen the ambiguity.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern in lowercase snake_case, such as list_databases, list_tables, and create_kafka_stream. The only slight deviation is connect_to_apache_iceberg, but it still follows the same verb-first convention.

    Tool Count5/5

    Seven tools is a well-scoped set for a Timeplus MCP server, covering database exploration, SQL execution, Kafka integration, and Iceberg connectivity without bloating the surface.

    Completeness4/5

    The toolset covers core querying, table/database listing, and Kafka stream ingestion plus Iceberg connection. Minor gaps exist around resource management (e.g., creating/dropping regular databases or streams), but the main read and integration workflows are supported.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to manage and monitor Apache Kafka clusters through natural language, providing real-time operations, health monitoring, consumer lag analysis, and temporal trend detection for intelligent cluster management.
      -
    • A
      license
      B
      quality
      B
      maintenance
      Enables AI agents to interact with Microsoft Fabric Real-Time Intelligence services, allowing for seamless data querying, analysis, and streaming capabilities.
      39
      5,551 PyPI
      134
      MIT
    • A
      license
      B
      quality
      C
      maintenance
      Enables AI assistants to connect to 17+ databases and query/analyze data using natural language via MCP and HTTP APIs, supporting platforms like Claude Desktop, Cursor, and VS Code.
      42
      26 npm
      MIT