Tdcv2

io.github.NickLiapinv0.1.1Updated Sep 29, 2026

Deterministic test data from a .tdc config, generated locally by the TDCv2 engine.

VerifiedSTDIODesktop onlyData & Analytics

Installation

In SourceWeft

  1. Open Tdcv2 in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

TDCv2 for AI agents

Let your coding agent make test data with TDCv2: it writes a small .tdc config, the TDCv2 engine generates the rows on your machine, and the same config gives the same file, byte for byte, every time you run it. CSV, JSON, SQL inserts or any text format; fields that agree with each other; exact shares; related tables; data packs for 95 languages and 198 countries.

Two parts, one version:

  • a skill — teaches the agent the TDC language, the workflow and the traps (skills/tdcv2);
  • an MCP server, tdcv2-mcp — the same, as tools: check a config, generate, find data packs, summarise a file, read the docs (mcp/).

Install

Claude Code — the plugin brings both the skill and the server:

sh
claude plugin marketplace add NickLiapin/tdcv2-agentsclaude plugin install tdcv2@tdcv2

Codex, Copilot, Gemini CLI, Cursor and other agents that read skills — put the skill where your agent looks for it:

sh
npx -y tdcv2-mcp install-skill            # ~/.claude/skills/tdcv2npx -y tdcv2-mcp install-skill --agents   # ~/.agents/skills/tdcv2npx -y tdcv2-mcp install-skill --project  # ./.claude/skills/tdcv2npx -y tdcv2-mcp install-skill --dir <skills folder>

Any MCP client (Claude Desktop, Cursor, VS Code…):

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

On Windows use "command": "npx.cmd" if the client cannot start npx. Everything needs Node.js 20 or newer.

Then ask in plain words — "500 customers from 20 countries as CSV", "a pytest test for validate_user on 50 different users" — and the agent takes it from there: writes the config, checks it with the engine, generates, and hands you the file together with the config that reproduces it.

Privacy

The engine runs locally. Neither the skill nor the server sends your data or your configs anywhere. The server reads .tdc files and writes generated files only inside the project folder it is started in.

Network access, all of it:

  • the plugin starts the server with npx -y tdcv2-mcp@<the plugin's version> (scripts/mcp-launch.mjs), so the first start downloads that exact version and its dependencies, the TDCv2 engine among them, from the npm registry;
  • npx -y tdcv2-mcp … in the commands above does the same;
  • data packs are downloaded only when you or the agent run tdcv2 pack add.

Nothing else is fetched, and nothing is sent.

Versions

This release, 0.1.1, is checked against TDCv2 0.3.3. The skill's reference is built from the engine's documentation for that version; with another engine version the agent reads that version's pages, and the engine's own check has the last word.

License

MIT

Source: README.md at commit 4599a06

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.1.1LatestSep 29, 2026