🇬🇧 English · 🇷🇺 Русский

Roistat MCP

Ask what changed between ad spend and sales.

Compare periods, follow a change in lead volume and inspect the orders or calls behind a report. Roistat MCP gives your assistant access to analytics and CRM-linked data from the projects you allow, while masking phone numbers, email addresses and visitor IPs in supported responses.

Quick start · Connect your assistant · Issues

Try asking your assistant:

Compare last week with the previous week for my project: marketing cost, leads, sales and revenue. Separate changes supported by the data from hypotheses that need checking.

What you can do

Related MCP server: KrystalView MCP Server

Quick start

Prefer a ready package? Install the release and generate your client configuration. No source checkout is required.

Install Python 3.12–3.14 and uv. Clone with Git or download the ZIP. With a ZIP, open the extracted directory and skip the first two commands.

You need a Roistat API key and the IDs of the projects you want to make available. The wizard saves the key locally and configures the project list.

git clone https://github.com/zai-one/roistat-mcp.git
cd roistat-mcp
uv sync --frozen
uv run --frozen python scripts/configure.py
uv run --frozen roistat-mcp --config mcp.local.json --check-config

The wizard creates a local configuration and stores secrets in private files. It refuses to overwrite an existing setup. --check-config validates local settings; the first request below checks your account connection.

Connect your assistant

Add this configuration to an MCP client that uses mcpServers, such as Claude Desktop or Cursor. Replace /ABSOLUTE/PATH/ with your absolute path; Windows JSON paths can use forward slashes, such as D:/Tools/.

{
  "mcpServers": {
    "roistat": {
      "command": "uv",
      "args": [
        "--directory",
        "/ABSOLUTE/PATH/roistat-mcp",
        "run",
        "--frozen",
        "roistat-mcp",
        "--config",
        "/ABSOLUTE/PATH/roistat-mcp/mcp.local.json"
      ]
    }
  }
}

The client starts the MCP server for you. Refresh its tool list, then make your first request. For clients with a different config format, reuse the same command and args; uv must be available to the client process.

First request

List the available Roistat projects and the metrics supported for an analytics report. Ask me which project to use.

You should see projects accessible to your API key and the supported report catalogue. Select a project from the server allowlist before asking for a report; an empty or partial response is not proof of zero activity.

If tools do not appear, check the absolute path, whether the client can find uv, and the --check-config result. For access errors, check account credentials and permissions. Installation and troubleshooting.

Access and limits

Choose the same attribution model when comparing periods. Custom-metric discovery does not make every metric queryable: the report tool uses a defined metric list. Changes to Roistat data need separate configuration and approval.

Authenticated HTTP is available for a server deployment. See HTTP setup, configuration and permissions and Python package integration.

uv sync --frozen --all-groups
uv run --frozen python scripts/verify.py
uv run --frozen python scripts/verify_install.py

Tests use synthetic fixtures. A passing test run does not establish live provider connectivity.

Built by ZAI.ONE

ZAI.ONE is a digital agency working on websites, SEO, advertising and analytics. We also build tools that connect AI assistants to everyday work. Talk to us on Telegram about setup, automation or an integration for your team.

Use and feedback

You may install and use this project for your own accounts under LicenseRef-ZAI-ONE. This is not an open-source license. Third-party notices remain in NOTICE. If it helps, give the repository a ⭐. Missing something or found a bug? Open an issue. I'm working on this project; accepted improvements are implemented here. Support is not guaranteed.