Anomaly AI
io.github.anomaly-aiv1.0.0Updated Sep 29, 2026
AI data analyst: ask about your Excel, CSV, GA4 or database data and get charts and dashboards back
Overview
AI-generated overview
Lets an assistant act as an AI data analyst, answering questions about Excel, CSV, GA4 or database data and returning charts and dashboards.
- What it does
- Anomaly AI is a remote MCP server that positions itself as an AI data analyst. According to its description, you can ask questions about your Excel, CSV, GA4 or database data and get charts and dashboards back. The manifest lists no tools, so the exact tool names and parameters are not documented here.
- When to use it
- Consider it when you want an assistant to explore spreadsheet exports, CSV files, Google Analytics 4 data or database tables conversationally and produce visual output. It is aimed at analysis and reporting rather than code or infrastructure work.
- Requirements
- A remote MCP endpoint at over streamable HTTP; no packages, environment variables or headers are declared. The manifest declares no authentication, but the description implies your data must be reachable by the service, which may require connecting or uploading data sources.
Before you install
The description says the server works with your Excel, CSV, GA4 and database data, so data you ask about is likely sent to a third-party service; check its handling of sensitive or regulated data before use. No credentials or authentication method are declared in the manifest, so confirm how access to your data sources is secured.
Installation
In SourceWeft
- Open Anomaly AI in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"anomaly": {
"type": "http",
"url": "https://mcp.findanomaly.ai/mcp"
}
}
}Tools
0Tool metadata has not been indexed yet.
Version history
1- v1.0.0LatestSep 29, 2026
