# Tdcv2

> Tdcv2 is an open-source MCP server for developer tools. Generate repeatable fake and test data locally from a .tdc config: CSV, JSON or SQL. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** CLI, self-hosted
- **Repository:** https://github.com/nickliapin/tdcv2-agents
- **MCP Registry name:** io.github.NickLiapin/tdcv2
- **Categories:** [developer tools](https://ai-powered.com/categories/developer-tools), [databases](https://ai-powered.com/categories/databases)
- **Listing updated:** 2026-11-18

## About

Think of it as Faker for whole datasets. The agent writes a small .tdc config, the TDCv2 engine generates rows on your own machine, and the same config yields the same file byte for byte on every run. Fields can agree with each other, shares can be exact, tables can relate, and data packs cover 95 languages and 198 countries.

The repository ships two parts at one version: a skill that teaches the agent the TDC language and common traps, and the tdcv2-mcp server whose tools check a config, generate, find and install data packs, summarise a file and read the docs. Install it as a Claude Code plugin, or add the npx command to any MCP client; Node.js 20 or newer is required.

The README spells out its network use: the first start downloads the package from npm, packs download only when asked, and a config using an http generator sends the named values to that URL. The server reads .tdc files and writes output only inside the project folder.

## Features

- **Reproducible output:** The same config produces an identical file every run.
- **Multiple formats:** Writes CSV, JSON, SQL inserts or any text format.
- **Consistent fields:** Fields agree with each other and tables can be related.
- **Language data packs:** Packs cover 95 languages and 198 countries.
- **Local generation:** Rows are generated on your machine and not sent anywhere.

## Good for

- Seed a database with realistic rows
- Create 500 customers from 20 countries as CSV
- Generate pytest fixtures with varied users
- Produce demo data for a product presentation

## Install

### Claude Code (Terminal)

```sh
claude mcp add tdcv2 -- npx -y tdcv2-mcp
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "tdcv2": {
      "command": "npx",
      "args": [
        "-y",
        "tdcv2-mcp"
      ]
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "tdcv2": {
      "command": "npx",
      "args": [
        "-y",
        "tdcv2-mcp"
      ]
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "tdcv2": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "tdcv2-mcp"
      ]
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "tdcv2": {
      "command": "npx",
      "args": [
        "-y",
        "tdcv2-mcp"
      ]
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "tdcv2": {
      "command": "npx",
      "args": [
        "-y",
        "tdcv2-mcp"
      ]
    }
  }
}
```

## Tools

- `tdc_pack_add`: Downloads and installs a data pack; the client asks you to allow it.

## FAQ

### Does my data leave my machine?

The README says neither the skill nor the server sends your data or configs anywhere; generation is local.

### What does it need?

Node.js 20 or newer and an MCP client such as Claude Desktop, Cursor or VS Code.

### Can I get the same file twice?

Yes, the same config gives the same file byte for byte.

### What licence is it?

MIT.

### Is Tdcv2 free?

Yes. Tdcv2 is open source, so you can use and self-host it for free.

### How do I add Tdcv2 to Claude Code?

Run this command in your terminal: claude mcp add tdcv2 -- npx -y tdcv2-mcp

### What are the best alternatives to Tdcv2?

The closest alternatives to Tdcv2 are REA, Context7, Chrome DevTools MCP, Codebase Memory and GitHub.

## Where this comes from

- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Context7](https://ai-powered.com/mcp/context7): Context7 is a freemium MCP server for developer tools.
- [Chrome DevTools MCP](https://ai-powered.com/mcp/chrome-devtools-mcp-2): Chrome DevTools MCP is an open-source MCP server for browser automation.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [awesome-mcp-servers](https://ai-powered.com/mcp/awesome-mcp-servers-2): awesome-mcp-servers is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.

---
Source: https://ai-powered.com/mcp/tdcv2
