Skip to content
Back to search

quick-data-mcp

Prompt focused MCP Server for .json and .csv agentic data analytics for Claude Code

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/disler--quick-data-mcp/badge.svg)](/listings/disler--quick-data-mcp)

HTML

<a href="/listings/disler--quick-data-mcp"><img src="/api/listings/disler--quick-data-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

To use the Quick Data MCP server:

1. **Navigate to the MCP server directory**:

   cd quick-data-mcp/

2. **Configure for your MCP client**:

   # Copy the sample configuration
   cp .mcp.json.sample .mcp.json

   # Edit .mcp.json and update the --directory path to your absolute path
   # Example: "/Users/yourusername/path/to/quick-data-mcp"

3. **Test the server**:

   uv run python main.py

See [quick-data-mcp/README.md](quick-data-mcp/README.md) for complete setup and usage documentation.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 107 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # MCP From Zero: Quick Data
  2. > Purpose: Learn to build Powerful Model Context Protocol (MCP) servers by scaling tools into reusable agentic workflows (ADWs aka Prompts w/tools).
  3. ## Quick-Data
  4. > Quick-Data is a MCP server that gives your agent arbitrary data analysis on .json and .csv files.
  5. >
  6. > We use quick-data as a concrete use case to experiment with the MCP Server elements specifically: Prompts > Tools > Resources.
  7. >
  8. > See [quick-data-mcp](quick-data-mcp/README.md) for details on the MCP server
  9. <img src="./images/mcp-server-prompts.png" alt="MCP Server Prompts" style="max-width: 800px;">
  10. ## Leading Questions
  11. We experiment with three leading questions:
  12. 1. How can we MAXIMIZE the value of custom built MCP servers by using tools, resources, and prompts TOGETHER?
  13. 2. What's the BEST codebase architecture for building MCP servers?
  14. 3. Can we build an agentic workflow (prompt w/tools) that can be used to rapidly build MCP servers?
  15. ## Understanding MCP Components
  16. MCP servers have three main building blocks that extend what AI models can do:
  17. ### Tools
  18. **What**: Functions that AI models can call to perform actions.
  19. **When to use**: When you want the AI to DO something at a low to mid atomic level based on your domain specific use cases.
  20. **Example**:
  21. ```python
  22. @mcp.tool()
  23. async def create_task(title: str, description: str) -> dict:
  24. """Create a new task."""
  25. # AI can call this to actually create tasks
  26. return {"id": "123", "title": title, "status": "created"}
  27. ```
  28. ### Resources
  29. **What**: Data that AI models can read and access.
  30. **When to use**: When you want the AI to READ information - user profiles, configuration, status, or any data source.
  31. **Example**:
  32. ```python
  33. @mcp.resource("users://{user_id}/profile")
  34. async def get_user_profile(user_id: str) -> dict:
  35. """Get user profile by ID."""
  36. # AI can read this data to understand users
  37. return {"id": user_id, "name": "John", "role": "developer"}
  38. ```
  39. ### Prompts
  40. **What**: Pre-built conversation templates that start specific types of discussions.
  41. **When to use**: When you want to give the AI structured starting points for common, repeatable workflows for your domain specific use cases.
  42. **Example**:
  43. ```python
  44. @mcp.prompt()
  45. async def code_review(code: str) -> str:
  46. """Start a code review conversation."""
  47. # AI gets a structured template for code reviews
  48. return f"Review this code for security and performance:\n{code}"
  49. ```
  50. ## Quick Decision Guide
  51. - **Need AI to take action?** → Use **Tools**
  52. - **Need AI to read data?** → Use **Resources**
  53. - **Need Reusable Agentic Workflows (ADWs)?** → Use **Prompts**
  54. ## Quick Setup
  55. To use the Quick Data MCP server:
  56. 1. **Navigate to the MCP server directory**:
  57. ```bash
  58. cd quick-data-mcp/
  59. ```
  60. 2. **Configure for your MCP client**:
  61. ```bash
  62. # Copy the sample configuration
  63. cp .mcp.json.sample .mcp.json
  64. # Edit .mcp.json and update the --directory path to your absolute path
  65. # Example: "/Users/yourusername/path/to/quick-data-mcp"
  66. ```
  67. 3. **Test the server**:
  68. ```bash
  69. uv run python main.py
  70. ```
  71. See [quick-data-mcp/README.md](quick-data-mcp/README.md) for complete setup and usage documentation.
  72. ## Resources
  73. - MCP Clients: https://modelcontextprotocol.io/clients
  74. - Claude Code Resource Support Github Issue: https://github.com/anthropics/claude-code/issuesç/545
  75. ## Master AI Coding
  76. Learn to code with AI with foundational [Principles of AI Coding](https://agenticengineer.com/principled-ai-coding?y=jprompt)
  77. Follow the [IndyDevDan youtube channel](https://www.youtube.com/@indydevdan) for more AI coding tips and tricks.
  78. Use the best Agentic Coding Tool: [Claude Code](https://docs.anthropic.com/en/docs/claude-code/overview)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.