logo
Login
Cover image
MCP-Collama-Postgres
Private

MCP-Collama-Postgres

Try Now
2025-04-14

3 years

Works with Finder

0

Github Watches

0

Github Forks

0

Github Stars

🚀 MCP-Powered Streamlit Dashboard with Ollama + PostgreSQL

A modern data analysis tool that lets you:

  • Query your PostgreSQL database with natural language
  • Run SQL manually or generate it using LLMs (Ollama)
  • Analyze data with charts, statistics, and export to CSV

🧠 Prompt-to-SQL Flow

graph TD
    A[🧑 User types a data question] --> B[Streamlit sends prompt to Ollama API]
    B --> C[Ollama generates SQL query as text]
    C --> D[Streamlit extracts the SQL]
    D --> E[Streamlit sends SQL to MCP server]
    E --> F[MCP executes query on PostgreSQL]
    F --> G[Results returned to Streamlit]
    G --> H[📊 Results shown + Chart + CSV Export]

📦 Architecture

  • Streamlit – UI + charting
  • MCP (FastMCP) – Tools/resources for SQL query and table listing
  • PostgreSQL – Stores your company data
  • Ollama – LLM that translates natural language prompts to SQL

📌 Features

✅ Natural language → SQL
✅ Charting (bar/line/time series)
✅ CSV download
✅ Statistical summary
✅ Prompt explainability with raw output
✅ Auto-detect date/time fields
✅ LLM integration with llama3 (configurable)

🛠️ Getting Started

git clone <this-repo>
cd postgres-mcp-server
docker-compose up --build

⚙️ Env Configuration

MCP_API_URL=http://mcp-server:3333/mcp
OLLAMA_URL=http://ollama:11434/api/generate

📤 Prompt Example

“List departments with average salary > 50000”

👉 Translated to SQL:

SELECT department, AVG(salary) FROM employees GROUP BY department HAVING AVG(salary) > 50000;

Why is this a good use case for MCP?

🔗 MCP makes it dead simple to expose structured tools like SQL queries to LLMs. 🎯 Agents can discover and call your tools without hardcoding logic. 💬 You get the best of both worlds — interpretability, flexibility, and control.

Whether you're building internal tools, research dashboards, or intelligent agents — this pattern is reusable, secure, and 100% local.

📄 License

MIT

相关推荐

港口

港口

  • av

    • 毫不费力地使用一个命令运行LLM后端，API，前端和服务。

    2 (1)
    1panel

    1panel

  • 1Panel-dev

    • 🔥1Panel提供了直观的Web接口和MCP服务器，用于在Linux服务器上管理网站，文件，容器，数据库和LLMS。

    2 (1)
    Rulego

    Rulego

  • rulego

    • ⛓️Rulego是一种轻巧，高性能，嵌入式，下一代组件编排规则引擎框架。

    3.7 (10)
    很棒的llm-resourses

    很棒的llm-resourses

  • WangRongsheng

    • 🧑‍🚀 llm 资料总结（数据处理、模型训练、模型部署、 o1 模型、mcp 、小语言模型、视觉语言模型）|摘要世界上最好的LLM资源。

    3.5 (4)
    群

    群

  • Onelevenvy

    • Flock是一个基于工作流程的低音平台，可快速构建聊天机器人，抹布和协调多代理团队，由Langgraph，Langchain，Langchain，Fastapi和Nextjs提供支持。（羊群工作流工作流的低代码平台，rag rag rag 用于快速构建聊天机器人、 rag temant Agent fastem temantfaster和muti-agent agagent应用

    3.2 (6)
    pdfmathtranslate

    pdfmathtranslate

  • Byaidu

    • PDF科学纸翻译带有保留格式的pdf -基于ai完整保留排版的pdf文档全文双语翻译

    2 (1)
    n8n

    n8n

  • n8n-io

    • 具有本机AI功能的公平代码工作流程自动化平台。将视觉构建与自定义代码，自宿主或云相结合，400+集成。

    3 (1)
    CPP-MCP

    CPP-MCP

  • hkr04

    • 轻巧的C ++ MCP（模型上下文协议）SDK

    3 (1)
    LLM命令

    LLM命令

  • sigoden

    • 使用普通的bash/javascript/python函数轻松创建LLM工具和代理。

    1 (1)
    Langbot

    Langbot

  • RockChinQ

    • 😎简单易用、🧩丰富生态 -大模型原生即时通信机器人平台| 适配QQ / 微信（企业微信、个人微信） /飞书 /钉钉 / discord / telegram / slack等平台| 支持chatgpt，deepseek，dify，claude，基于LLM的即时消息机器人平台，支持Discord，Telegram，微信，Lark，Dingtalk，QQ，Slack

    5 (1)
    代理商

    代理商

  • modelscope

    • 开始以更轻松的方式开始构建具有LLM授权的多代理应用程序。

    2 (1)

    Reviews

    2 (5)
    Avatar
    user_AN1bW5aK
    2025-04-23

    As a dedicated user of mcp-ollama-postgres, I can confidently say that this tool has been a game-changer for my database management tasks. Created by rajeevchandra, its seamless integration with PostgreSQL and user-friendly interface have significantly boosted my productivity. The initial setup was straightforward, and the welcome information provided clear guidance. Highly recommend this for efficient database handling!

    Avatar
    user_htYF6BE7
    2025-04-23

    I've been using the mcp-ollama-postgres app by rajeevchandra and I am thoroughly impressed. The seamless integration with PostgreSQL and the intuitive design have significantly boosted my productivity. The welcome information is clear and helpful, making the initial setup a breeze. Overall, a fantastic tool for any developer working with PostgreSQL databases. Highly recommend!

    Avatar
    user_hY4FVtD0
    2025-04-23

    As a dedicated user of mcp-ollama-postgres, I am thoroughly impressed with this tool. It seamlessly integrates PostgreSQL with Ollama, significantly enhancing my database management workflows. Rajeevchandra has crafted an intuitive and user-friendly experience, making complex operations straightforward. Highly recommended for anyone looking to streamline their database tasks.

    Avatar
    user_JCkvnTQd
    2025-04-23

    As a loyal user of the mcp-ollama-postgres application, I am genuinely impressed by its robust integration and efficiency. Developed by rajeevchandra, this tool seamlessly connects Postgres databases for optimal performance and management. It simplifies complex processes and provides intuitive navigation through its well-designed interface. It's truly an indispensable asset for database administrators and developers alike.

    Avatar
    user_7hh85nC3
    2025-04-23

    As a dedicated user of the mcp-ollama-postgres application, I am thoroughly impressed by its seamless integration and robust functionality. Developed by rajeevchandra, this tool has significantly optimized my database management tasks. The user-friendly interface and reliable performance make it an essential asset for anyone working with PostgreSQL. Highly recommended!