ToolFront MCP server for AI agents

ToolFront is an MCP (Model Context Protocol) server that helps AI models discover and interact with your data sources. It serves as a bridge between AI applications and various data sources like databases, APIs, and documents, allowing AI models to learn about your data on-the-fly and answer questions accurately.

Installation

ToolFront can be installed and run using either UV or Docker, with integration options for AI frameworks and IDEs.

Prerequisites

uv or Docker to run the MCP server (uv is recommended)
URLs for your databases and APIs
API key (optional) for using the continuous evaluation and learning features

Setting Up in AI Frameworks/IDEs

First, create an MCP configuration for your chosen environment:

Using UV (Recommended)

{
  "toolfront": {
    "command": "uvx",
    "args": [
      "toolfront[all]",
      "postgresql://user:pass@host:port/db",
      "https://api.com/openapi.json?api_key=key",
      "--api-key", "YOUR-API-KEY"
    ]
  }
}

Using Docker

{
  "toolfront": {
    "command": "docker",
    "args": [
      "run",
      "-i",
      "antidmg/toolfront",
      "postgresql://user:pass@host:port/db",
      "https://api.com/openapi.json?token=my_token",
      "--api-key", "YOUR-API-KEY"
    ]
  }
}

For Docker with local file access:

{
  "toolfront-docker": {
    "command": "docker",
    "args": [
      "run",
      "-i",
      "-v", "/Users/you/Documents:/app/docs",
      "antidmg/toolfront",
      "postgresql://user:pass@host:port/db",
      "file:///app/docs",
      "--api-key", "YOUR-API-KEY"
    ]
  }
}

Running Directly

You can also run ToolFront directly from the command line:

# Using uvx and SSE
uvx "toolfront[postgres]" "postgres://user:pass@host:port/db" "https://api.com/spec.json?token=my_token" --transport sse

# Using Docker and stdio
docker run -i antidmg/toolfront "postgres://user:pass@host:port/db" "https://api.com/spec.json?token=my_token" --transport stdio

For Docker with local file access:

# Mount local directories as volumes
docker run -i -v "/path/to/local/docs:/app/docs" antidmg/toolfront "file:///app/docs" --transport stdio

Supported Data Sources

Databases

ToolFront supports various database types:

Database	Extras	URL Format
BigQuery	`bigquery`	`bigquery://{project-id}?credentials_path={path-to-account-credentials.json}`
Databricks	`databricks`	`databricks://token:{token}@{workspace}.cloud.databricks.com/{catalog}?http_path={warehouse-path}`
DuckDB	`duckdb`	`duckdb://{path-to-database.duckdb}`
MySQL	`mysql`	`mysql://{user}:{password}@{host}:{port}/{database}`
PostgreSQL	`postgresql`, `postgres`	`postgres://{user}:{password}@{hostname}:{port}/{database-name}`
Snowflake	`snowflake`	`snowflake://{user}:{password}@{account}/{database}`
SQL Server	`mssql`, `sqlserver`	`mssql://{user}:{password}@{server}:{port}/{database}`
SQLite	`sqlite`	`sqlite://{path-to-database.sqlite}`

APIs

ToolFront supports APIs with OpenAPI or Swagger specifications. Some common examples:

API	Specification URL
Wikipedia	`https://en.wikipedia.org/api/rest_v1/?spec`
GitHub	`https://raw.githubusercontent.com/github/rest-api-description/main/descriptions/api.github.com/api.github.com.json`
Stripe	`https://raw.githubusercontent.com/stripe/openapi/master/openapi/spec3.json`
Slack	`https://raw.githubusercontent.com/slackapi/slack-api-specs/master/web-api/slack_web_openapi_v2.json`
Discord	`https://raw.githubusercontent.com/discord/discord-api-spec/main/specs/openapi.json`

For APIs requiring authentication, append your API key or token to the specification URL.

Document Libraries

ToolFront can work with various document types:

{
  "toolfront": {
    "command": "uvx", 
    "args": [
      "toolfront[document]",
      "file:///path/to/your/documents"
    ]
  }
}

Supported formats include PDF, Word, PowerPoint, Excel, JSON, Markdown, TXT, XML, YAML, and RTF.

Available Tools

ToolFront provides various tools that AI agents can call:

Tool	Description
`discover`	List all configured databases, APIs, and document libraries
`search_documents`	Search documents by name pattern or similarity
`read_document`	Read document contents with smart pagination
`search_endpoints`	Search API endpoints by pattern or similarity
`search_tables`	Search database tables by pattern or similarity
`sample_table`	Get sample rows from a database table
`inspect_table`	Show structure and columns of a database table
`inspect_endpoint`	Show structure and parameters of an API endpoint
`query_database`	Run read-only SQL queries against databases
`request_api`	Make requests to API endpoints
`search_queries`	Retrieve and learn from relevant query samples (requires API key)
`search_requests`	Retrieve and learn from relevant requests (requires API key)

Troubleshooting Tips

If you encounter connection issues:

Run ToolFront directly from the command line to see detailed error messages
Double-check your database and API URLs
For localhost databases with Docker, add --network HOST before the image name
When using Docker with local files, ensure paths are correctly mounted as volumes

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "toolfront" '{"command":"uvx","args":["toolfront[all]","DATABASE-URL-1","DATABASE-URL-2","--api-key","YOUR-API-KEY"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "toolfront": {
            "command": "uvx",
            "args": [
                "toolfront[all]",
                "DATABASE-URL-1",
                "DATABASE-URL-2",
                "--api-key",
                "YOUR-API-KEY"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "toolfront": {
            "command": "uvx",
            "args": [
                "toolfront[all]",
                "DATABASE-URL-1",
                "DATABASE-URL-2",
                "--api-key",
                "YOUR-API-KEY"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect