Timeplus MCP Server
An MCP server for Timeplus, enabling Large Language Models (LLMs) to interact with Timeplus streaming data through SQL queries.
Features
Prompts
generate_sql: Provides LLMs with the ability to translate natural language queries into SQL for Timeplus.
Tools
run_sql:- Executes SQL queries on a Timeplus cluster.
- Input:
sql(string): The SQL query to execute. - By default, all Timeplus queries are run with
readonly = 1for safety. SetTIMEPLUS_READ_ONLYtofalseto enable DDL/DML.
list_databases:- Lists all databases on the Timeplus cluster.
list_tables:- Lists all tables in a specified database.
- Input:
database(string): The name of the database.
list_kafka_topics:- Lists all topics in a Kafka cluster.
explore_kafka_topic:- Shows messages in a Kafka topic.
- Input:
topic(string): The name of the topic.message_count(int): The number of messages to show (default is 1).
create_kafka_stream:- Sets up a streaming ETL in Timeplus to save Kafka messages locally.
- Input:
topic(string): The name of the topic.
Configuration
Configuration involves setting environment variables to connect to your Timeplus instance. Key variables include TIMEPLUS_HOST, TIMEPLUS_USER, and TIMEPLUS_PASSWORD.
Development
Instructions are provided for setting up a development environment using Docker Compose and uv for dependency management.




