Cover image
Try Now
2025-04-01

3 years

Works with Finder

1

Github Watches

0

Github Forks

0

Github Stars

MCP Server: Trend Data Persister

This project implements a Model Context Protocol (MCP) server using Python (fastmcp) to persist trend data (upward or downward) into a PostgreSQL database.

The server exposes a single tool, persist-trend-data, which accepts:

  1. datasource_url: The connection string for the target PostgreSQL database.

  2. json_data: A JSON object representing the trend. It must match one of the following schemas:

    • Upward Trend:
      {
        "trend": "upward",
        "rockstars": [
          { "name": "string", "department": "string", "amount": integer },
          ...
        ]
      }
      
    • Downward Trend:
      {
        "trend": "downward",
        "culprits": [
          { "name": "string", "department": "string", "amount": integer },
          ...
        ]
      }
      

Functionality:

Based on the trend value in json_data:

  • If trend is "upward", it ensures a table named upward_trend_rockstars exists (with columns id, name, department, amount). It then inserts the data from the rockstars array into this table.
  • If trend is "downward", it ensures a table named downward_trend_culprits exists (with the same columns). It then inserts the data from the culprits array into this table.
  • The tool uses Pydantic for input validation and psycopg2 to interact with the PostgreSQL database.

Prerequisites

  • Python (>=3.10 recommended, as specified in pyproject.toml)
  • make
  • uv (Optional, Makefile will fallback to python -m venv and pip if uv is not found)
  • Access to a running PostgreSQL database.

Setup and Running

A Makefile is provided for convenience.

  1. Clone/Navigate: Go into the project directory:
    cd /path/to/mcp-server-trend-persister
    
  2. Run the Server:
    make
    
    The setup will install dependencies, run the mcp server and inspect it. Also the mcp server will listen for requests via standard input/output.

Makefile Targets

The following targets are available in the Makefile:

  • make install: Creates/updates the .venv virtual environment and installs dependencies using uv (preferred) or pip.
  • make run: Runs the MCP server (persister.py) using the Python interpreter from .venv.
  • make inspect: Inspects the tools defined in persister.py using the MCP inspector (npx @modelcontextprotocol/inspector uv run persister.py). Depends on install.
  • make lint: Placeholder for running code linters (e.g., Ruff, Black).
  • make clean: Removes the virtual environment, cache files, and other build artifacts.
  • make help: Shows the list of available targets.

Integration with MCP Clients

Configure your MCP client (like the one mentioned in the context) to connect to this server. When using the Makefile, the command to launch the server simplifies.

Example configuration snippet:

{
    "mcpServers": {
        "trend-persister": {
            "command": "make",
            "args": [
                "run" // Target to execute
            ],
            "cwd": "/Users/julian/Documents/Code/Learning/MCP/mcp-server-trend-persister" // Important: Set the working directory
        },
        // ... other servers
    }
}

Ensure the cwd path points to the correct project directory where the Makefile resides.

Example Tool Request

An MCP client would send a request like:

{
  "toolName": "persist-trend-data",
  "arguments": {
    "datasource_url": "postgresql://your_user:your_password@your_host:5432/your_db",
    "json_data": {
      "trend": "upward",
      "rockstars": [
        { "name": "Alice", "department": "Sales", "amount": 50000 },
        { "name": "Bob", "department": "Engineering", "amount": 60000 }
      ]
    }
  }
}

相关推荐

  • NiKole Maxwell
  • I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Alexandru Strujac
  • Efficient thumbnail creator for YouTube videos

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Lists Tailwind CSS classes in monospaced font

  • lumpenspace
  • Take an adjectivised noun, and create images making it progressively more adjective!

  • Yasir Eryilmaz
  • AI scriptwriting assistant for short, engaging video content.

  • https://appia.in
  • Siri Shortcut Finder – your go-to place for discovering amazing Siri Shortcuts with ease

  • apappascs
  • 发现市场上最全面,最新的MCP服务器集合。该存储库充当集中式枢纽,提供了广泛的开源和专有MCP服务器目录,并提供功能,文档链接和贡献者。

  • ShrimpingIt
  • MCP系列GPIO Expander的基于Micropython I2C的操作,源自ADAFRUIT_MCP230XX

  • jae-jae
  • MCP服务器使用剧作《无头浏览器》获取网页内容。

  • HiveNexus
  • 一个适用于中小型团队的AI聊天机器人,支持DeepSeek,Open AI,Claude和Gemini等车型。 专为中小团队设计的ai聊天应用,支持deepSeek,打开ai,claude,双子座等模型。

  • ravitemer
  • 一个功能强大的Neovim插件,用于管理MCP(模型上下文协议)服务器

  • patruff
  • Ollama和MCP服务器之间的桥梁,使本地LLMS可以使用模型上下文协议工具

    Reviews

    3 (1)
    Avatar
    user_1lne7Kd3
    2025-04-16

    I've been using the File Merger MCP Server by exoticknight and it's been a game-changer for my workflow. The interface is intuitive, and it significantly reduces the time it takes to merge multiple files. Highly recommend for anyone needing efficient file management! Check it out here: https://mcp.so/server/mcp-file-merger/exoticknight.