Generate-Data
MCP server for Generate-Data.com: dataset generation, AI schema design, Project management.
Connector by ns-3e · GitHub account verified by the MCP Registry
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/ns-3e-generate-data-mcp
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.
- Tools
- 4 read · 0 write · 0 delete · 3 not yet classified
- Secrets
- 1 (API keys, tokens or passwords)
- Install scripts
- Not scanned yet
- Runs as
- Python package
Tools by what they do 7
Read from the source code; the running server may list different tools.
Read 4 · Look things up without changing anything.
gd_get_field_type_optionsgd_get_usagegd_list_field_typesgd_list_projects
Not yet classified 3 · We could not tell from the name and description.
gd_design_schemagd_generate_datasetgd_generate_project
Secrets and settings it asks for
Secrets: values you paste in that let it act as you.
GENERATE_DATA_API_KEY
Other settings (environment variables or headers).
GENERATE_DATA_API_BASE_URL
Tools (7)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
gd_design_schemaDesign a dataset schema from natural language — one tool for both the first proposal and follow-up refinements. Behavior branches on args: - First call (propose): pass only `prompt` (and optionally `locale`, e.g. 'en_US', 'fr_FR'). `messages`/`current_schema` left unset. - Refine call: pass BOTH `messages` (the running conversation, list of `{"role": "user"|"assistant", "content": str}`) AND `current_schema` (the schema object returned by the prior call) together — `prompt` is still required by the signature but is not sent upstream for a refine call. If only one of `messages`/`curre…
gd_generate_datasetGenerate synthetic dataset rows from a field list. Use this when the user wants actual generated data (as opposed to schema design or field-type discovery). `fields` is a list of `{"name": str, "type": str, "options": dict}` (get valid `type` values from `gd_list_field_types`/`gd_get_field_type_options`). `format` must be one of `csv`, `json`, `xml`, `parquet`, `zip` (anything else returns an `unsupported_format` error). `num_rows` caps upstream row count; `settings` is an optional passthrough dict of generation settings. Returns the JSON envelope: on success `data.content` (csv/json/xml) or `…
gd_generate_projectGenerate all tables in a Project and download the result (Premium tier only). `project_id` must be a positive integer (get one from `gd_list_projects`). `format` must be one of `csv`, `json`, `xml`, `parquet`, `zip` (default `zip`; anything else returns `unsupported_format`). Non-Premium API keys get a `tier_forbidden` error — upgrade the Generate-Data.com plan to use this tool. Returns the JSON envelope: on success `data.content` (csv/json/xml) or `data.content_base64` (parquet/zip, base64-encoded — never decode these as utf-8) plus `data.size_bytes`/`data.truncated`. On failure returns a cor…
gd_get_field_type_optionsGet the configuration option schema for one field type (e.g. what options `email` or `date` accept). Use this before building a `fields` entry for `gd_generate_dataset` that needs non-default options. `field_type` must match `^[a-z0-9_]+$` (lowercase letters, digits, underscore only) — anything else returns `invalid_input` without calling upstream. Returns the option schema in `data`.
gd_get_usageGet current API key usage stats (calls today, tier, limits). Use this to check remaining quota or confirm which tier the configured API key has before attempting a premium-only call. Takes no arguments. Returns the usage stats in `data`.
gd_list_field_typesList all available field types grouped by category. Use this to discover valid `type` values before calling `gd_generate_dataset` or to look up which category a field type belongs to. Takes no arguments. Returns the categorized field-type catalog in `data.categories`.
gd_list_projectsList the user's Projects (Premium tier only). Use this to discover `project_id` values before calling `gd_generate_project`. `limit` (default 20, max 100) and `offset` (default 0) page through the results; results are paginated client-side since the upstream API returns the full list. Non-Premium API keys get a `tier_forbidden` error — upgrade the Generate-Data.com plan to use this tool. Returns the page in `data` (`items`, `limit`, `offset`, `total_count`, `has_more`, `next_offset`).
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Weekly downloads
- 26
- Last commit
- Sep 8, 2026 (1 month ago)
- Last release
- Aug 3, 2026 (2 months ago)
- Last package publish
- Aug 3, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026) and the package registry.
Details
- Registry name
io.github.ns-3e/generate-data-mcp- Version
- 2.0.1
- Auth
- API key
- Packages
- pypi generate-data-mcp
- License
- MIT
- Repository
- github.com/ns-3e/generate-data-mcp
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Cite this page
Generate-Data MCP server. Agent Mart. https://agentmart.dev/connectors/ns-3e-generate-data-mcp (last updated 2026-10-24)