广告合作
MCP.so
登录
C

Clutter MCP Server

@michaelhologram

代码仓库

基本信息

分类

开发工具

传输方式

stdio

作者

michaelhologram

提交者

michaelhologram

关于 Clutter MCP Server

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.

Clutter MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

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

Clutter MCP Server 工具

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.

概览

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

常见问题

1

What transport does Clutter use?

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

2

Is authentication required to use Clutter?

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

3

How many tools does Clutter provide?

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

4

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.

评论

开发工具 分类下的更多 MCP 服务器

LocalCan

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

82
S

SecondSim

econdSim provisions real UK mobile numbers (non-VoIP) via eSIM, built for freelancers, sole traders, small businesses, and enterprise teams. Unlike VoIP apps and virtual numbers, SecondSim numbers register as genuine phy

Foremerge

naw103

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

50

AptiBuild AI — Career Intelligence

ParklandBuilds

AptiBuild AI — Career Intelligence MCP Server Structured career decision scaffolding for AI agents. Provides personality-conditioned business idea generation, official BLS OEWS wage data, FRED labor market signals, and

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

1
广告合作