mostlyai-mcp-server by mostly-ai - MCP Server

MOSTLY AI MCP Server

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)

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

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.

Debug

We recommend to use the Anthropic's MCP Inspector for testing and debugging by running npx @modelcontextprotocol/inspector.

mostly-ai/mostlyai-mcp-server

get_platform_info

get_user_info

get_models

get_computes

list_connectors

get_connector

create_connector

get_connector_locations

get_connector_schema

read_connector_data

write_connector_data

query_connector

list_generators

get_generator

poll_generator_progress

train_generator

clone_generator

get_synthetic_dataset

poll_synthetic_dataset_progress

generate_synthetic_dataset

list_synthetic_datasets

probe_generator