About Onx Mcp Server
Onx Mcp Server connects the Onspring API to MCP for AI assistants that need to read and interact with Onspring data. Its tools cover apps, records, reports, and attachment files.
Key features
- 01Lists accessible apps and fields
- 02Retrieves and filters app records
- 03Reads reports and report data
- 04Fetches files from attachment fields
- 05Checks the Onspring API connection
Use cases
- 01Query business records in Onspring apps
- 02Filter and page through records
- 03Read app reports for analysis
- 04Retrieve files attached to records
MCP support
The MCP server exposes tools for reading Onspring apps, fields, records, reports, and attachment files, as well as querying records and checking the API connection.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @stevanfreeborn/onx-mcp-serverONSPRING_API_KEYSecretONSPRING_BASE_URLLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
8Saved tool list · updated 2w ago
This tool takes no parameters.
Details
From the project READMEOnspring MCP Server
A Model Context Protocol (MCP) server implementation that integrates with Onspring's API, allowing AI assistants to access and manipulate data stored in Onspring instances.
Description
This server provides a bridge between AI assistants and Onspring instances through the Model Context Protocol. It enables MCP clients to read and interact with your Onspring data, providing capabilities like:
- Retrieving lists of apps and their fields
- Fetching records from apps
- Running queries against apps
- Accessing report data
- Retrieve files from attachment fields
Table of Contents
Installation
Prerequisites
- Node.js
- An Onspring instance with API access
- An Onspring API key with appropriate permissions
Installation Steps
- Install the package globally:
npm install -g @stevanfreeborn/onx-mcp-server
Or use it directly via npx:
npx @stevanfreeborn/onx-mcp-server
Building from Source
If you want to build from source:
# Clone the repository
git clone https://github.com/your-username/onx-mcp-server.git
cd onx-mcp-server
# Install dependencies
npm install
# Build the project
npm run build
# Start the server
npm start
Usage
In order to use the server, you will need to configure it in the MCP client of your choice. Each MCP client should provide instructions on setting up a MCP server. You will also need to make sure the required environment variables are set. See the Configuration section for more details.
Configuration
The server requires that the following environment variables are set:
| Variable | Description | Default |
|---|---|---|
ONSPRING_API_KEY | Your Onspring API key | (Required) |
ONSPRING_BASE_URL | The base URL for the Onspring API | https://api.onspring.com |
Connecting to Claude Desktop
Claude Desktop is a popular MCP client. To connect the Onspring MCP server to Claude Desktop, follow these steps:
-
Find the
claude_desktop_config.jsonfile. Please reference this documentation for more information on where to find this file: For Claude Desktop Users. -
Open the
claude_desktop_config.jsonfile in a text editor and add the following configuration:
{
"mcpServers": {
"onx-mcp-server": {
"command": "npx",
"args": ["-y", "@stevanfreeborn/onx-mcp-server"],
"env": {
"ONSPRING_API_KEY": "your_onspring_api_key",
"ONSPRING_BASE_URL": "https://api.onspring.com"
}
}
}
}
Note
The specific command and arguments may vary based on your setup.
Available Tools
The MCP Server exposes the following tools for AI assistants to interact with Onspring:
checkConnectionTool
Verifies that the server can connect to the Onspring API using the provided credentials.
getAppsTool
Retrieves a list of all accessible apps in the Onspring instance.
getFieldsTool
Gets all fields for a specified app.
Parameters:
name: The name of the app
getRecordsTool
Retrieves records from an app with specified fields.
Parameters:
appName: The name of the appfields: Array of field names to retrievepageNumber: The page number to start from (1-based)numberOfPages: The number of pages to retrieve
getReportsTool
Gets all reports available for a specified app.
Parameters:
appName: The name of the app
getReportDataTool
Retrieves data from a specified report.
Parameters:
appName: The name of the appreportName: The name of the reportdataType: The type of report data to retrieve (optional)
queryRecordsTool
Queries records from an app using a filter.
Parameters:
appName: The name of the appfields: Array of field names to retrievefilter: A filter object to restrict the resultspageNumber: The page number to start from (1-based)numberOfPages: The number of pages to retrieve
getFileTool
Retrieves a file stored in an attachment field.
Parameters:
appName: The name of the appfieldName: The name of the attachment fieldrecordId: The ID of the record containing the filefileName: The name of the file to retrieve
Development
Setup Development Environment
# Install dependencies
npm install
# Run in development mode (watches for changes)
npm run dev
Testing
The project uses Vitest for testing:
# Run tests
npm test
# Run tests with coverage
npm run test:coverage
# Run tests with UI
npm run test:ui
Inspecting the Server
You can use the MCP Inspector to test the server:
npm run inspect
License
This project is licensed under the MIT License - see the LICENSE.md file for details.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.