Query Live OData Services in Zed Editor via CData Connect AI
Zed is a high-performance, open-source code editor built for speed and collaboration. Its built-in AI agent panel supports LLM-powered interactions and MCP (Model Context Protocol) tool integrations, enabling developers to access live external data sources directly within the editor.
By integrating Zed with CData Connect AI through the built-in MCP (Model Context Protocol) Server, the Zed AI agent gains governed, real-time access to live OData services. This enables developers to query schemas, retrieve records, and explore OData services without leaving the editor or writing custom integration code.
This article walks through configuring OData connectivity in Connect AI, registering the CData MCP Server in Zed, and querying live OData services from the Zed agent panel.
About OData Data Integration
CData simplifies access and integration of live OData services data. Our customers leverage CData connectivity to:
- Access OData versions 2.0, 3.0, and 4.0, working with legacy services and the latest features and capabilities.
- Leverage advanced query options, including $filter, $select, and $expand, enhancing data retrieval from 3rd party tools.
- Use Server-side execution of aggregation and grouping to minimize data transfer and boost performance.
- Authenticate securely using a variety of schemes, including Azure AD, digest, negotiate, NTLM, OAuth, and more means secure authentication with every connection.
- Use SQL stored procedures to manage OData service entities - listing, creating, and removing associations between entities.
Customers use CData's solutions to regularly integrate their OData services with preferred tools, such as Power BI, MicroStrategy, or Tableau, and to replicate data from OData services to their databases or data warehouses.
Getting Started
Step 1: Configure OData connectivity for Zed
Connectivity to OData from Zed is made possible through CData Connect AI's Remote MCP Server. To interact with OData services from Zed, start by creating and configuring a OData connection in CData Connect AI.
- Log into Connect AI, click Sources, and then click Add Connection
- Select OData from the Add Connection panel
-
Enter the necessary authentication properties to connect to OData.
The User and Password properties, under the Authentication section, must be set to valid OData user credentials. In addition, specify a URL to a valid OData server organization root or OData services file.
- Click Save & Test
- 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 Zed. It is best practice to create a separate PAT for each integration to maintain granular access control.
- Click the gear icon () at the top right of the Connect AI app to open Settings
- On the Settings page, go to the Access Tokens section and click Create PAT
- Give the PAT a descriptive name and click Create
- Copy the token when displayed and store it securely. It will not be shown again
With the OData connection configured and a PAT generated, Zed can now connect to OData services through Connect AI.
Step 2: Configure Connect AI in Zed
Now, let's register the CData Connect AI MCP endpoint in Zed so that the built-in AI agent can discover and call live data tools.
- Download and install Zed
- Open the agent panel by pressing Ctrl + Shift + /, or by clicking the sparkle icon at the bottom right of the editor
-
In the agent panel, click the ... (toggle agent menu) and select Add Custom Server from the dropdown
- Select the Configure Remote option to configure CData's MCP
-
An Add MCP Server dialog opens displaying a remote server configuration template. Replace the placeholder content with the following JSON:
{ "cdata": { "url": "https://mcp.cloud.cdata.com/mcp", "headers": { "Authorization": "Basic your_base64_encoded_email_PAT" } } }Note: Combine your Connect AI email and PAT in the format email:PAT, Base64 encode the combined string, and prefix it with Basic. For example, given [email protected]:ABC123...XYZ, the header value becomes something like: Basic dXNlckBteWRvbWFpbjphSzkvbVB4Mi9Rcjd2TjQ...
- Click Add Server or press Ctrl + Enter to register the MCP server
Configure an LLM provider
Zed requires at least one LLM provider to power the agent's reasoning. Configure a provider so the agent can interpret queries and call MCP tools through Connect AI.
- Click the ... (toggle agent menu) and select Settings
- Under LLM Providers, expand your preferred provider (e.g., Anthropic, OpenAI, Google AI) and enter your API key
-
Under Model Context Protocol (MCP) Servers, confirm that cdata appears with a green dot and the toggle is enabled
With the MCP server registered and an LLM provider configured, the Zed agent is ready to query live OData services through Connect AI.
Step 3: Query live OData services from the Zed agent
With the integration complete, use the Zed agent panel to explore and interact with live OData services through natural language prompts.
- Open the agent panel using Ctrl + Shift + / and start a new thread
-
Enter a prompt to interact with your data, for example:
- List all catalogs in my cdata connection
- Show the available schemas and tables for OData
- Query the top 5 records from a table in OData services
-
The agent calls the CData Connect AI MCP Server and returns live results from OData services
At this point, your Zed agent communicates with the CData Connect AI MCP Server and retrieves live OData services through remote MCP tools directly from the editor.
Get CData Connect AI
To access 300+ SaaS, Big Data, and NoSQL sources directly from your cloud applications, try CData Connect AI today! Download a free 14-day trial of CData Connect AI today, and as always, our world-class Support Team is available to assist you with any questions you may have.