MCP.so
Sign In
C

Clutter

@michaelhologram

Repository

About Clutter

Synthetic data generator MCP server. Generates realistic companies, documents, and structured data — e.g. to populate SharePoint/test/demo systems. 19 tools, stdio, requires CLUTTER_API_KEY.

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "clutter": {
      "command": "npx",
      "args": [
        "-y",
        "clutter-mcp"
      ],
      "env": {
        "CLUTTER_API_KEY": "<YOUR_CLUTTER_API_KEY>"
      }
    }
  }
}

Tools

20

Return the authenticated Clutter user for the configured API key.

Your Clutter API usage (request counts by route) over a rolling window + the daily quota.

List all of your Clutter projects (top-level tenant containers).

Create a new Clutter project. Returns the project (with its id).

Delete a project and EVERYTHING under it — all its organisations, runs, datasets, metadata and artefacts (S3 + DB). Irreversible.

List the synthetic organisations in a project.

Start building a synthetic organisation from a prompt. Returns 202 with an orgId. The build runs in the background (minutes) — then poll get_org, or call wait_for_org to block until ready. Omit projectId to auto-create a project (named after the generated company) — the simplest path.

Get an organisation including its full org.json structure. Check `org.status`.

Poll an org until its build reaches a terminal state (ready/failed) or the timeout. Returns the final org summary.

Ask a grounded natural-language question about an organisation (synchronous, one-shot answer).

Delete an organisation and ALL its runs/artefacts (S3 + DB). Irreversible.

List the generation runs under an organisation.

Launch a generation run. Returns 202 with a runId — poll get_run or call wait_for_run. kind + params: • doc_generator → { prompt, doc_number (≤300), file_types:[docx|pdf|xlsx|eml|jpg], structure:'flat'|'nested', target_system?, allow_underscores? } • data_generator → { prompt, row_count (≤2000), data_format:'xlsx'|'csv'|'json', data_fields?, target_system? } • doc_metadata_gen → { sourceRunId (a completed doc_generator run), data_format, data_fields?, target_system? }

Get a run's status + progress counts. Poll this until status is terminal.

Poll a run until it reaches a terminal state (complete/partial/failed) or the timeout. Returns the final run status.

List the documents generated by a run (title, format, folderPath, status).

Get a short-lived presigned download URL for a single generated document.

Start building a single ZIP of all of a run's documents. Poll get_zip_url after.

Get a presigned download URL for a run's ZIP (409 until the build is ready).

Delete a run and its artefacts (S3 + DB). Leaves the parent org intact. Irreversible.

Overview

What is Clutter?

Clutter is an MCP (Model Context Protocol) server for generating realistic synthetic data. It creates companies, documents, and other structured data, and is designed for populating systems like SharePoint, test environments, or demo systems.

How to use Clutter?

The server runs over the stdio transport and requires a CLUTTER_API_KEY environment variable to be set. It exposes 19 tools for data generation. No installation steps or specific commands are detailed in the README.

Key features of Clutter

  • Generates realistic companies, documents, and structured data
  • Provides 19 distinct tools for synthetic data creation
  • Runs over the stdio transport protocol
  • Requires an API key for authentication

Use cases of Clutter

  • Populating SharePoint sites with realistic sample data
  • Filling test environments with consistent, non‑sensitive data
  • Creating demo datasets for presentations or evaluations

FAQ from Clutter

What transport does Clutter use?

Clutter uses the stdio transport, which is the standard method for MCP servers running as subprocesses.

Is authentication required to use Clutter?

Yes, the server requires the CLUTTER_API_KEY environment variable to be set before it will accept requests.

How many tools does Clutter provide?

Clutter exposes 19 tools for generating different types of synthetic data.

What kind of data can Clutter generate?

Clutter can generate realistic companies, documents, and other structured data, suitable for populating SharePoint, test systems, or demo environments.

Frequently asked questions

What transport does Clutter use?

Clutter uses the stdio transport, which is the standard method for MCP servers running as subprocesses.

Is authentication required to use Clutter?

Yes, the server requires the `CLUTTER_API_KEY` environment variable to be set before it will accept requests.

How many tools does Clutter provide?

Clutter exposes 19 tools for generating different types of synthetic data.

What kind of data can Clutter generate?

Clutter can generate realistic companies, documents, and other structured data, suitable for populating SharePoint, test systems, or demo environments.

Comments

Basic information

Category

Developer Tools

Transports

stdio

Author

michaelhologram

Submitted by

michaelhologram

More Developer Tools MCP servers

TaskerArmy Agent

TaskerArmy

Ask Claude or ChatGPT what Shopify theme optimization tasks are pending on your store, a remote MCP server for TaskerArmy Agent accounts.

Reelier

Maxime Houle

Agents make claims. Reelier writes receipts — record an agent's tool-call workflow once, replay it deterministically at 0 tokens, and diff runs to catch drift.

discoverGPT

Joe Monastiero

discoverGPT is visualAI's unified MCP gateway for AI commerce, exposing 29 tools across four capabilities on one canonical product catalog: trimodal search (natural-language, precise-color, and image-similarity), AI cata

Windframe

Windframe MCP gives your AI the design taste needed to create consistent, production-ready UI that feels intentionally designed. Available at https://windframe.dev/mcp

Skycloak

Manage your Skycloak-hosted Keycloak: clusters, realms, apps, SSO and users, from any MCP client.