Interact with Live JSON Data in Meta Muse via CData Connect AI

Muse is Meta's personal AI agent for iOS, Android, and the web, built on the Muse Spark models. It connects to remote model context protocol (MCP) servers, so you can point Muse at a governed data source and let it discover and call live data tools.

Connect Muse to CData Connect AI through its Remote MCP Server, and Muse gains governed, real-time access to live JSON data. You can explore data, fetch records, and interact with objects using natural language prompts, with every request running against authorized sources.

This article shows you how to configure JSON connectivity in Connect AI, generate a personal access token, create a custom connector to the Connect AI Remote MCP Server in Muse, and interact with live JSON data from Muse.

Step 1: Configure JSON connectivity for Meta Muse

Connectivity to JSON from Muse is made possible through Connect AI's Remote MCP Server. To interact with JSON services from Muse, start by creating and configuring a JSON connection in Connect AI.

1. Log into Connect AI, click Sources, and then click Add Connection

2. Select JSON from the Add Connection panel

3. Enter the necessary authentication properties to connect to JSON.

   See the Getting Started chapter in the data provider documentation to authenticate to your data source: The data provider models JSON APIs as bidirectional database tables and JSON files as read-only views (local files, files stored on popular cloud services, and FTP servers). The major authentication schemes are supported, including HTTP Basic, Digest, NTLM, OAuth, and FTP. See the Getting Started chapter in the data provider documentation for authentication guides.

   After setting the URI and providing any authentication values, set DataModel to more closely match the data representation to the structure of your data.

   The DataModel property is the controlling property over how your data is represented into tables and toggles the following basic configurations.

   • Document (default): Model a top-level, document view of your JSON data. The data provider returns nested elements as aggregates of data.
   • FlattenedDocuments: Implicitly join nested documents and their parents into a single table.
   • Relational: Return individual, related tables from hierarchical data. The tables contain a primary key and a foreign key that links to the parent document.

   See the Modeling JSON Data chapter for more information on configuring the relational representation. You will also find the sample data used in the following examples. The data includes entries for people, the cars they own, and various maintenance services performed on those cars.

   
4. Click Save & Test
5. Navigate to the Permissions tab and update user-based permissions

Add a Personal Access Token

A Personal Access Token (PAT) is used to authenticate the connection to Connect AI from Muse. It is best practice to create a separate PAT for each integration to maintain granular access control.

1. Click the gear icon () at the top right of the Connect AI app to open Settings
2. On the Settings page, go to the Access Tokens section and click Create PAT
3. Give the PAT a descriptive name and click Create

4. Copy the token when displayed and store it securely. It will not be shown again

With the JSON connection configured and a PAT generated, Muse can now connect to JSON services through Connect AI.

Step 2: Create a custom connector to the Connect AI MCP Server in Meta Muse

Muse has no manual "add MCP server" form. Instead, you ask Muse in plain language to build a custom connector that points at the Connect AI Remote MCP Server, a hosted, public HTTPS endpoint that speaks streamable HTTP. Muse builds the connector on its secure VM using the official MCP SDK, then discovers and calls the available Connect AI data tools.

1. Open Muse on iOS, Android, or the web and start a new chat
2. Ask Muse to build a custom connector to the Connect AI Remote MCP Server, giving it the server URL and noting that the endpoint is a hosted MCP server over streamable HTTP, for example:
   Create a custom connector to CData Connect AI. It is a hosted MCP server over streamable HTTP at https://mcp.cloud.cdata.com/mcp and it requires an Authorization header.
3. When Muse prompts for credentials, it opens a secure entry flow, separate from the chat, that saves the value in its Secure Credentials Store. Enter the Authorization header value in the format Basic your_base64_encoded_email_PAT

   Note: For the Authorization value, base64 encode email:PAT and prefix it with Basic. Enter it only in Muse's secure credential prompt, never in the chat.

4. Muse connects to the Connect AI MCP Server and lists the available data tools. Review the custom connector confirmation, then click Continue. When Muse offers to save the integration as a skill, choose yes so the connector is available in every future chat

With the custom connector saved, the Connect AI tools are available to Muse in any chat.

Step 3: Interact with live JSON services from Meta Muse

With the integration complete, interact with live JSON services directly from Muse through natural language prompts.

1. In a Muse chat, type a prompt that uses the Connect AI connector, for example:
   • Use the CData Connect AI connector to list all available connections
   • Show the available objects and fields for JSON
   • Fetch the top 5 records from JSON
2. Approve the tool call in the Sentinel dialog when prompted
3. Muse calls the Connect AI MCP Server and returns live results from JSON services

At this point, Muse communicates with the Connect AI MCP Server and retrieves live JSON services through remote MCP tools directly from your chats.

Get started with CData Connect AI

With CData Connect AI, interact with hundreds of SaaS, big data, and NoSQL sources directly from your AI agents, models, and cloud applications. To explore more download a free 14-day trial today. Our Support Team is available to help with any questions you have.