GreptimeDB MCP Server

What does “greptimedb” MCP Server do?

The greptimedb MCP (Model Context Protocol) Server is a tool designed to bridge AI assistants with GreptimeDB, a powerful time-series database. It enables AI agents to securely and efficiently interact with GreptimeDB by providing structured access to database functionalities. This includes capabilities such as listing tables, reading table data, and executing SQL queries—all through well-defined MCP primitives. By exposing these actions in a controlled manner, greptimedb-mcp-server enhances development workflows, allowing AI-powered tools and assistants to analyze, explore, and manage database content safely and programmatically. This approach fosters responsible data access while enabling rich, context-aware interactions for data analysis, reporting, and automation.

List of Prompts

• list_prompts
  Lists all available prompts/templates for interaction.
• get_prompt
  Retrieves a specific prompt by its name.

List of Resources

• list_resources
  Lists database tables available in GreptimeDB.
• read_resource
  Reads data from a specified table/resource in the database.

List of Tools

• list_tools
  Lists all executable tools provided by the server.
• call_tool
  Executes a SQL command on the GreptimeDB database.

Use Cases of this MCP Server

• Database Table Discovery
  AI assistants can enumerate all tables in a GreptimeDB instance, aiding in schema exploration and data mapping for analytics and reporting.
• Data Querying and Analysis
  Agents can execute SQL queries to extract, aggregate, or analyze time-series data, supporting use cases from monitoring to trend analysis.
• Contextual Data Retrieval
  Enables AI agents to pull specific table data as context for LLM tasks, such as generating summaries, anomaly detection, or forecasting.
• Automated Reporting
  Scripted or AI-driven workflows can use the server to generate periodic reports by querying the latest data from GreptimeDB.
• Assisted Data Management
  Developers can use AI to interactively manage and inspect GreptimeDB contents, improving productivity in data engineering workflows.

How to set it up

Windsurf

1. Ensure Python and GreptimeDB are installed.
2. Set environment variables or provide command-line arguments for DB connection (GREPTIMEDB_HOST, GREPTIMEDB_PORT, etc.).
3. Add the MCP server to your Windsurf configuration:

   {
     "mcpServers": {
       "greptimedb": {
         "command": "greptimedb-mcp-server",
         "args": []
       }
     }
   }
   

4. Save your config and restart Windsurf.
5. Verify the server is available in your tool list.

Securing API keys:

{
  "mcpServers": {
    "greptimedb": {
      "command": "greptimedb-mcp-server",
      "args": [],
      "env": {
        "GREPTIMEDB_USER": "your_user",
        "GREPTIMEDB_PASSWORD": "your_password"
      }
    }
  }
}

Claude

1. Install the server: pip install greptimedb-mcp-server
2. Edit claude_desktop_config.json (see README for path).
3. Add:

   {
     "mcpServers": {
       "greptimedb": {
         "command": "greptimedb-mcp-server",
         "args": []
       }
     }
   }
   

4. Save and restart Claude Desktop.
5. Confirm MCP server availability in Claude UI.

Cursor

1. Install greptimedb-mcp-server via pip.
2. Locate Cursor’s configuration file for MCP servers.
3. Insert:

   {
     "mcpServers": {
       "greptimedb": {
         "command": "greptimedb-mcp-server",
         "args": []
       }
     }
   }
   

4. Save and restart Cursor.
5. Check for server in Cursor’s tool integrations.

Cline

1. Install and configure greptimedb-mcp-server as above.
2. Edit Cline’s MCP server config:

   {
     "mcpServers": {
       "greptimedb": {
         "command": "greptimedb-mcp-server",
         "args": []
       }
     }
   }
   

3. Save and restart Cline.
4. Validate the server is accessible as a tool.

Note about securing API keys

Always use environment variables (not plaintext in config) for sensitive credentials:

{
  "mcpServers": {
    "greptimedb": {
      "command": "greptimedb-mcp-server",
      "args": [],
      "env": {
        "GREPTIMEDB_USER": "your_user",
        "GREPTIMEDB_PASSWORD": "your_password"
      },
      "inputs": {}
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "greptimedb": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “greptimedb” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the information above, greptimedb-mcp-server provides solid MCP primitives for database access, tooling, and prompt/resource management, but lacks explicit sampling/roots support. The documentation is clear, and setup is straightforward for several platforms.

I would rate this MCP server a 7/10 for its practical features, clear documentation, and security notes, but with room for improvement in advanced MCP features (sampling/roots) and more user-oriented prompt templates.

MCP Score