How do I use MOSTLY AI MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MOSTLY AI MCP Server train a generator using my customer data connector" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

MOSTLY AI MCP Server

license GitHub stars

A Model Context Protocol (MCP) server with OAuth 2.1 support for LLM agents to interact with the MOSTLY AI Platform.

Available Tools

Tool	Description
`get_platform_info`	retrieve information about the platform
`get_user_info`	retrieve information about the current user
`get_models`	retrieve a list of available models of a specific type
`get_computes`	retrieve a list of available compute resources for tasks
`list_connectors`	list all available connectors
`get_connector`	get details of a specific connector
`create_connector`	create a new connector and optionally test the connection
`get_connector_locations`	list available locations (schemas, tables, buckets, etc.) for a connector
`get_connector_schema`	get the schema of a table or file at a connector location
`read_connector_data`	read data from a connector location
`write_connector_data`	write data to a connector location (currently disabled)
`query_connector`	execute a read-only SQL query against a connector's data source
`list_generators`	list all available generators
`get_generator`	get details of a specific generator
`poll_generator_progress`	poll progress of a generator training job
`train_generator`	train a new generator with provided data or configuration
`clone_generator`	clone an existing generator
`get_synthetic_dataset`	get details of a specific synthetic dataset
`poll_synthetic_dataset_progress`	poll progress of a synthetic dataset generation job
`generate_synthetic_dataset`	generate a synthetic dataset using a generator
`list_synthetic_datasets`	list all available synthetic datasets
`probe_generator`	probe a generator for a new synthetic dataset (quick sample)

Usage of Remote Server

Prerequisites

An MCP host that supports the latest MCP specification and remote servers, such as Claude, VS Code and Cursor.

Installation

Claude Desktop or Web UI

Search and tools -> Add integrations -> Add integration -> Set Integration name to the name of your choice (e.g., mostlyai) and Integration URL to https://mcp.mostly.ai/sse.

VS Code (>= v1.101)

Install in VS Code

For quick installation, please use the one-click button above. Alternatively, one can add the following JSON to .vscode/mcp.json (for the workspace) or the global settings.json (for the user).

{
  "servers": {
    "mostlyai": {
      "url": "https://mcp.mostly.ai/sse"
    }
  }
}

Cursor Install in Cursor

For quick installation, please use the one-click button above. Alternatively, one can add the following JSON to ~/.cursor/mcp.json.

{
    "mcpServers": {
      "mostlyai": {
        "url": "https://mcp.mostly.ai/sse"
      }
    }
}

Development

Setup virtual environment

uv sync --frozen

Start the server locally

Set the necessary environment variables (see .env.example)
uv run mostlyai-mcp-server --port 8000
Connect to the server with the configuration described in the above section, but change the url to http://localhost:8000/sse.