workday-mcp-gateway-by-cdata

CData's Read-Only Model Context Protocol (MCP) Server Adapter for Workday

:heavy_exclamation_mark: This implementation provides a constrained, read-only interface. For comprehensive data manipulation capabilities (CRUD operations) and a simpler setup experience, consider deploying our complimentary CData MCP Server for Workday (Beta).

Core Objective

This read-only MCP adapter was engineered to empower Large Language Models (such as Claude Desktop) with the ability to query real-time data sourced from Workday, underpinned by the robust CData JDBC Driver for Workday.

The CData JDBC Driver establishes connectivity to Workday by representing its data structures as conventional relational SQL models.

This server component encapsulates that driver, exposing Workday data through a straightforward MCP interface. Consequently, LLMs can retrieve pertinent, up-to-the-minute information by formulating plain-language requests—eliminating the necessity for direct SQL construction.

Deployment Instructions

1. Obtain the source repository: bash git clone https://github.com/cdatasoftware/workday-mcp-server-by-cdata.git cd workday-mcp-server-by-cdata

2. Compile the server artifact: bash mvn clean install

   This action generates the executable JAR: CDataMCP-jar-with-dependencies.jar 3. Acquire and install the CData JDBC Driver for Workday: https://www.cdata.com/drivers/workday/download/jdbc 4. Activate the CData JDBC Driver license: * Navigate to the driver's installed lib directory. Typical paths are: * (Windows) C:\Program Files\CData\CData JDBC Driver for Workday\ * (Mac/Linux) /Applications/CData JDBC Driver for Workday/ * Execute the licensing utility: java -jar cdata.jdbc.workday.jar --license * Input your credentials and use "TRIAL" or your permanent license key when prompted. 5. Define the data source connection parameters: * Execute java -jar cdata.jdbc.workday.jar to launch the Connection String configuration utility.

   • Configure the necessary parameters (e.g., authentication details). If OAuth is involved, browser-based authentication will commence.
   • Upon a successful connection test, capture the resulting JDBC connection string for subsequent use.
   • Formulate a configuration properties file (e.g., workday.prp) detailing the JDBC mapping:
   • Prefix: Identifier prefix for exposed tools.
   • ServerName: Arbitrary name for the data service endpoint.
   • ServerVersion: Version designation for the service.
   • DriverPath: Absolute file system location of the JDBC driver JAR.
   • DriverClass: The fully qualified name of the JDBC Driver implementation class (e.g., cdata.jdbc.workday.WorkdayDriver).
   • JdbcUrl: The connection string obtained in the previous step.
   • Tables: Optionally restrict access by listing specific table names; leave empty for full schema exposure. env Prefix=workday_live ServerName=WorkdayAnalyticsGateway ServerVersion=2.1.0 DriverPath=ABSOLUTE/PATH/TO/cdata.jdbc.workday.jar DriverClass=cdata.jdbc.workday.WorkdayDriver JdbcUrl=jdbc:workday:InitiateOAuth=GETANDREFRESH;User=... Tables=

Integration with AI Clients (e.g., Claude Desktop)

1. Construct or modify the client configuration file (e.g., claude_desktop_config.json) to incorporate the new MCP endpoint configuration within the mcpServers object.

   Windows Example

   { "mcpServers": { "workday_live": { "command": "C:\PATH\TO\java.exe", "args": [ "-jar", "C:\PATH\TO\CDataMCP-jar-with-dependencies.jar", "C:\PATH\TO\workday.prp" ] }, ... } }

   Linux/Mac Example

   { "mcpServers": { "workday_live": { "command": "/usr/bin/java", "args": [ "-jar", "/opt/cdata/CDataMCP-jar-with-dependencies.jar", "/etc/configs/workday.prp" ] }, ... } }

   Ensure this configuration file is placed in the correct client application directory (e.g., for Claude Desktop): Windows Relocation bash copy C:\PATH\TO\claude_desktop_config.json %APPDATA%\Claude\claude_desktop_config.json

   Linux/Mac Relocation bash cp /PATH/TO/claude_desktop_config.json /Users/{user}/Library/Application\ Support/Claude/claude_desktop_config.json

2. Restart or refresh the AI client application to register the newly added MCP data access tools.

Crucial Note: A complete shutdown (ensuring no background processes remain via Task Manager/Activity Monitor) and subsequent relaunch of the client is often necessary for new MCP servers to become active.

Standalone Server Execution

Execute the server independently using the following invocation: bash java -jar /ABSOLUTE/PATH/TO/CDataMCP-jar-with-dependencies.jar /ABSOLUTE/PATH/TO/workday.prp

Constraint: The server communicates via standard input/output (stdio), restricting its utility to clients running on the identical host machine.

Operational Guidance

Once integrated via the MCP server configuration, the consuming AI agent can interrogate the underlying Workday repository by issuing natural language prompts. Explicit tool invocation is generally unnecessary. For instance, the agent might respond to queries such as: * "Query the current vacation balance for all employees in the 'Finance' department." * "Retrieve the names and locations of all open requisitions." * "List the most recent organizational structure changes that occurred last quarter."

Available Functions & Signatures

Tool names are prefixed according to the configuration (e.g., workday_live based on the example above). * workday_live_get_tables - Fetches the complete enumeration of accessible data entities. Follow up with workday_live_get_columns to inspect schema details. Output is CSV format, starting with headers. * workday_live_get_columns - Retrieves the schema definition (column names and types) for a specified table. Requires the table name as an argument. * workday_live_run_query - Executes arbitrary SQL SELECT statements against the Workday data model.

JSON-RPC Interaction Examples

For direct integration or scripting purposes, interact with the server following the JSON-RPC 2.0 specification. Below are illustrative request payloads:

Request to List Entities (workday_live_get_tables)

{ "jsonrpc": "2.0", "id": 101, "method": "tools/call", "params": { "name": "workday_live_get_tables", "arguments": {} } }

Request to Inspect Schema (workday_live_get_columns)

{ "jsonrpc": "2.0", "id": 102, "method": "tools/call", "params": { "name": "workday_live_get_columns", "arguments": { "table": "Employee_Data" } } }

Request to Execute SQL (workday_live_run_query)

{ "jsonrpc": "2.0", "id": 103, "method": "tools/call", "params": { "name": "workday_live_run_query", "arguments": { "sql": "SELECT EmployeeID, Name, TerminationDate FROM [Employee] WHERE IsTerminated = 0 AND HireDate < '2020-01-01'" } } }

Common Resolution Procedures

1. Server Visibility Issue: If the configured CData MCP Server fails to appear within the AI client interface, verify that the client application has been completely shut down and restarted.
2. Data Retrieval Failure: If the client connects but cannot fetch data, meticulously re-validate the connection string configuration within the .prp file against the string generated by the driver's utility tool.
3. Connection Errors: For persistent connectivity faults to the Workday source, engage the CData Support Team for specialized assistance.
4. MCP Server Feedback: For general usability issues or suggestions regarding the MCP server component itself, please contribute to the discussion on the CData Community.

Software Licensing

This server utility is distributed under the permissive MIT License. You are granted the liberty to employ, modify, and disseminate this software, contingent upon adherence to the MIT License terms. Detailed stipulations are available in the project's LICENSE file.

Comprehensive Driver Connectivity Support

[... Table Content Omitted for Brevity, but the list confirms Workday connectivity within a vast ecosystem ...] Workday is present in the final section, confirming support.

Background Context

WIKIPEDIA: Cloud computing is "a paradigm for enabling network access to a scalable and elastic pool of shareable physical or virtual resources with self-service provisioning and administration on-demand," according to ISO. It is commonly referred to as "the cloud".

== Key Attributes (NIST Essential Characteristics) == NIST defined five core attributes for cloud systems in 2011:

On-demand self-service: "A consumer can unilaterally provision computing capabilities, such as server time and network storage, as needed automatically without requiring human interaction with each service provider." Broad network access: "Capabilities are available over the network and accessed through standard mechanisms that promote use by heterogeneous thin or thick client platforms (e.g., mobile phones, tablets, laptops, and workstations)." Resource pooling: " The provider's computing resources are pooled to serve multiple consumers using a multi-tenant model, with different physical and virtual resources dynamically assigned and reassigned according to consumer demand." Rapid elasticity: "Capabilities can be elastically provisioned and released, in some cases automatically, to scale rapidly outward and inward commensurate with demand. To the consumer, the capabilities available for provisioning often appear unlimited and can be appropriated in any quantity at any time." Measured service: "Cloud systems automatically control and optimize resource use by leveraging a metering capability at some level of abstraction appropriate to the type of service (e.g., storage, processing, bandwidth, and active user accounts). Resource usage can be monitored, controlled, and reported, providing transparency for both the provider and consumer of the utilized service.

== Historical Precursors ==

The evolution toward cloud computing began in the 1960s with the advent of time-sharing concepts popularized through Remote Job Entry (RJE). During that decade, the prevailing model involved users submitting tasks to system operators who executed them on centralized mainframes. This era was characterized by intensive R&D into methods for democratizing access to high-capacity computation, focusing on optimizing infrastructure, platform layers, applications, and overall end-user productivity. The specific 'cloud' visual metaphor for abstract network services was first employed in 1994 by General Magic to describe the conceptual realm accessible by their Telescript mobile agents. David Hoffman, a specialist at General Magic, is generally credited with adapting this metaphor from its established use in telecommunications and networking. The term 'cloud computing' gained broader market recognition in 1996 when Compaq Computer Corporation drafted a strategic vision for future computational models and internet services, signaling an intent toward ubiquitous resource access.