MCP cover image
See in Github
2025-04-07

Execute SQL queries and manage databases seamlessly with Timeplus. Leverage powerful tools to interact with your data, Kafka topics, and Iceberg tables efficiently. Enhance your data workflows with a user-friendly interface and robust backend capabilities.

0

Github Watches

2

Github Forks

8

Github Stars

Timeplus MCP Server

PyPI - Version

An MCP server for Timeplus.

mcp-timeplus MCP server

Features

Prompts

  • generate_sql to give LLM more knowledge about how to query Timeplus via SQL

Tools

  • run_sql

    • Execute SQL queries on your Timeplus cluster.
    • Input: sql (string): The SQL query to execute.
    • By default, all Timeplus queries are run with readonly = 1 to ensure they are safe. If you want to run DDL or DML queries, you can set the environment variable TIMEPLUS_READ_ONLY to false.
  • list_databases

    • List all databases on your Timeplus cluster.
  • list_tables

    • List all tables in a database.
    • Input: database (string): The name of the database.
  • list_kafka_topics

    • List all topics in a Kafka cluster
  • explore_kafka_topic

    • Show some messages in the Kafka topic
    • Input: topic (string): The name of the topic. message_count (int): The number of messages to show, default to 1.
  • create_kafka_stream

    • Setup a streaming ETL in Timeplus to save the Kafka messages locally
    • Input: topic (string): The name of the topic.
  • connect_to_apache_iceberg

    • Connect to a database based on Apache Iceberg. Currently this is only available via Timeplus Enterprise and it's planned to make it available for Timeplus Proton soon.
    • Input: iceberg_db (string): The name of the Iceberg database. aws_account_id (int): The AWS account ID (12 digits). s3_bucket (string): The S3 bucket name. aws_region (string): The AWS region, default to "us-west-2". is_s3_table_bucket (bool): Whether the S3 bucket is a S3 table bucket, default to False.

Configuration

First, ensure you have the uv executable installed. If not, you can install it by following the instructions here.

  1. Open the Claude Desktop configuration file located at:

    • On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • On Windows: %APPDATA%/Claude/claude_desktop_config.json
  2. Add the following:

{
  "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\"}"
      }
    }
  }
}

Update the environment variables to point to your own Timeplus service.

  1. Restart Claude Desktop to apply the changes.

You can also try this MCP server with other MCP clients, such as 5ire.

Development

  1. In test-services directory run docker compose up -d to start a Timeplus Proton server. You can also download it via curl https://install.timeplus.com/oss | sh, then start with ./proton server.

  2. Add the following variables to a .env file in the root of the repository.

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. Run uv sync to install the dependencies. Then do source .venv/bin/activate.

  2. For easy testing, you can run mcp dev mcp_timeplus/mcp_server.py to start the MCP server. Click the "Connect" button to connect the UI with the MCP server, then switch to the "Tools" tab to run the available tools.

  3. To build the Docker image, run docker build -t mcp_timeplus ..

Environment Variables

The following environment variables are used to configure the Timeplus connection:

Required Variables

  • TIMEPLUS_HOST: The hostname of your Timeplus server
  • TIMEPLUS_USER: The username for authentication
  • TIMEPLUS_PASSWORD: The password for authentication

Optional Variables

  • TIMEPLUS_PORT: The port number of your Timeplus server
    • Default: 8443 if HTTPS is enabled, 8123 if disabled
    • Usually doesn't need to be set unless using a non-standard port
  • TIMEPLUS_SECURE: Enable/disable HTTPS connection
    • Default: "false"
    • Set to "true" for secure connections
  • TIMEPLUS_VERIFY: Enable/disable SSL certificate verification
    • Default: "true"
    • Set to "false" to disable certificate verification (not recommended for production)
  • TIMEPLUS_CONNECT_TIMEOUT: Connection timeout in seconds
    • Default: "30"
    • Increase this value if you experience connection timeouts
  • TIMEPLUS_SEND_RECEIVE_TIMEOUT: Send/receive timeout in seconds
    • Default: "300"
    • Increase this value for long-running queries
  • TIMEPLUS_DATABASE: Default database to use
    • Default: None (uses server default)
    • Set this to automatically connect to a specific database
  • TIMEPLUS_READ_ONLY: Enable/disable read-only mode
    • Default: "true"
    • Set to "false" to enable DDL/DML
  • TIMEPLUS_KAFKA_CONFIG: A JSON string for the Kafka configuration. Please refer to librdkafka configuration or take the above example as a reference.

相关推荐

  • microsoft
  • Python tool for converting files and office documents to Markdown.

  • sirmews
  • Read your Apple Notes with Claude Model Context Protocol

  • ttommyth
  • Vibe coding should have human in the loop! interactive-mcp: Local, cross-platform MCP server for interact with your AI Agent

  • kopfrechner
  • Interact seamlessly with GitLab repositories to manage merge requests and issues. Fetch details, add comments, and streamline your code review process with ease.

  • mzxrai
  • Chat with OpenAI models from Claude Desktop

  • nguyenvanduocit
  • 🚀 All-in-one MCP server with AI search, RAG, and multi-service integrations (GitLab/Jira/Confluence/YouTube) for AI-enhanced development workflows

  • magarcia
  • An implementation of Giphy integration with Model Context Protocol

    Reviews

    5 (0)