docusign -by-cdata

This MCP server provides a read-only interface to DocuSign data via the CData JDBC Driver for DocuSign. It wraps the JDBC driver and exposes the data as MCP tools that AI clients like Claude Desktop can query without writing SQL. After building and running the server, you can query DocuSign tables and columns through the standard MCP tool primitives (get_tables, get_columns, and run_query) using a per-server prefix (the server name is used as the prefix in tool names).

To use the server, configure Claude Desktop (or another MCP client) to add a new MCP server entry named after the server (for example, docusign). The exposed tools follow the pattern {servername}_get_tables, {servername}_get_columns, and {servername}_run_query. You typically do not call the tools directly; instead, ask the AI to retrieve data (e.g., how many envelopes are in a status, or what fields exist for a given table), and the client will invoke the appropriate tool under the hood. Example tool usage includes listing available tables, inspecting columns for a table, and running a SELECT query against the underlying data source.

Available tools and their descriptions:

• docusign_get_tables: Retrieves tables from the DocuSign data source.
• docusign_get_columns: Retrieves columns for a specified table (use the output to guide your queries).
• docusign_run_query: Executes a SQL SELECT query against the DocuSign data.

JSON-RPC examples demonstrate how to call these tools, including how to request table lists, column lists, and results from a query. Because this is a read-only server, write/update/delete capabilities are not exposed here.

Prerequisites:

• Java runtime (required to run the MCP server Jar)
• A built and packaged CData MCP Server jar (CDataMCP-jar-with-dependencies.jar)
• The CData JDBC Driver for DocuSign installed and licensed, and a prepared .prp file describing the JDBC connection

Step 1: Install Java (if not already installed)

• Windows: Download from Oracle/OpenJDK and install
• macOS/Linux: Use your package manager (e.g., brew install openjdk) and ensure java is on your PATH

Step 2: Build the MCP server

git clone https://github.com/cdatasoftware/docusign-mcp-server-by-cdata.git
cd docusign-mcp-server-by-cdata
mvn clean install

This should produce CDataMCP-jar-with-dependencies.jar in the target directory.

Step 3: Install and license the CData JDBC Driver for DocuSign (one-time)

• Download the driver from: https://www.cdata.com/drivers/docusign/download/jdbc
• Install according to the vendor instructions
• License the driver by running the command from the lib folder, as described in the setup guide: java -jar cdata.jdbc.docusign.jar --license (Enter your name, email, and TRIAL or license key when prompted.)

Step 4: Create a .prp file for your JDBC connection (example docusign.prp)

Prefix=docusign
ServerName=CDataDocusign
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.docusign.jar
DriverClass=cdata.jdbc.docusign.DocusignDriver
JdbcUrl=jdbc:docusign:InitiateOAuth=GETANDREFRESH;
Tables=

Save this as docusign.prp and place it in a known path.

Step 5: Run the MCP server

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/docusign.prp

Note: The server uses stdio, so it is intended to be used by clients running on the same machine.

Tips and caveats:

• This MCP server is read-only; write/update/delete capabilities are not exposed in this configuration.
• The server communicates over standard I/O and is intended for local usage with clients like Claude Desktop on the same machine.
• Ensure the JDBC driver is properly licensed and the .prp file correctly points to the driver and JDBC URL; any OAuth-based connections may require browser-based authentication during initial setup.
• If Claude Desktop cannot discover the MCP server, fully quit and re-launch Claude Desktop, and ensure the server process is running and accessible on the expected path.
• When sharing or migrating configurations, keep the path to the jar and the .prp file consistent, and be mindful of Windows vs. Linux/macOS path conventions in the configuration.
• If you encounter connection issues, verify the connection string (JdbcUrl) in the .prp file and test the connection using the CData JDBC Driver utility to ensure the data source is reachable.