generate-data-mcp

An MCP server forGenerate-Data.com— generate synthetic datasets, design schemas from natural language, and manage Projects, straight from your agent.

You need a Generate-Data.com API key first — create one inSettings → API Accessongenerate-data.com.

{ "mcpServers": { "generate-data": { "command": "uvx", "args": ["generate-data-mcp"], "env": { "GENERATE_DATA_API_KEY": "your-uuid-key-here" } } } }

uvxfetches and runs the latest published version on demand — no separate install step, nothing to update by hand. Restart your client and the 7gd_tools are available.

# run once, ad hoc: uvx generate-data-mcp # or install it as a persistent CLI tool: uv tool install generate-data-mcp

git clone https://github.com/ns-3e/generate-data-mcp.git cd generate-data-mcp pip install -e ".[dev]"

export GENERATE_DATA_API_KEY=your-key generate-data-mcp

Ask your agent something like"generate 50 rows of fake e-commerce customers as CSV"*and it will callgd_design_schemathengd_generate_dataseton its own.

A typical session looks like this — the agent chains tools on its own, you just describe the outcome:
- Discover what's possible.gd_list_field_types— see every field type, grouped by category.
- Design a schema.gd_design_schema(prompt="E-commerce customers with name, email, and signup date")— proposes afieldsarray from plain English.
- Generate the data.gd_generate_dataset(fields=..., num_rows=10, format="csv")— returns the rows.
- Refine if needed.Callgd_design_schemaagain, this time passingmessages(the running conversation) +current_schema(the prior result) together — it refines instead of proposing fresh.

Every tool returns the same envelope:{"ok": true, "summary": "...", "data": {...}}on success, or{"ok": false, "error": {"code": ..., "message": ...}}on failure — errors always tell you what to do next, never a raw stack trace.

{ "env": { "GENERATE_DATA_API_BASE_URL": "http://localhost:8000" } }

Point at a locally running Django backend instead of the hosted API.

v2.0.0 renames every tool (breaking change). Old name → new name:

- generate_data→gd_generate_dataset
- list_field_types→gd_list_field_types
- get_field_options→gd_get_field_type_options
- propose_schema→gd_design_schema(first call, nomessages/current_schema)
- refine_schema→gd_design_schema(passmessages+current_schematogether)
- get_api_usage→gd_get_usage
- list_projects→gd_list_projects(now paginated:limit/offset)
- generate_project→gd_generate_project(binary formats now returned base64-encoded, not corrupted utf-8)

- gd_generate_dataset— Generate synthetic dataset rows from a field list.format:csv,json,xml,parquet, orzip(binary formats return base64-encoded).
- gd_list_field_types— List all available field types grouped by category. Takes no arguments.
- gd_get_field_type_options— Get the configuration option schema for one field type.field_typemust match^[a-z0-9_]+$.
- gd_design_schema— Design a dataset schema from natural language, or refine an existing one — one tool for both the first proposal and follow-up conversation turns.
- gd_get_usage— Get current API key usage stats: calls today, tier, limits. Takes no arguments.

- gd_list_projects— List the user's Projects, paginated (limit/offset, default 20/0).
- gd_generate_project— Generate all tables in a Project and download the result. Same format/binary rules asgd_generate_dataset.

git clone https://github.com/ns-3e/generate-data-mcp.git cd generate-data-mcp pip install -e ".[dev]" pytest tests/ -v

Docs live ongenerate-data.com. See this repo's tool docstrings (generate_data_mcp/server.py) for the authoritative request/response shapes.

Build and deploy full-stack Next.js apps with 98 tools for React, AWS, and MongoDB