A read-only MCP server by CData that enables LLMs to query live data from Exact Online.
CData's Model Context Protocol (MCP) Server for Exact Online
:heavy_exclamation_mark: This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free CData MCP Server for Exact Online (beta).
We created this read-only MCP Server to allow LLMs (like Claude Desktop) to query live data Exact Online supported by the CData JDBC Driver for Exact Online.
CData JDBC Driver connects to Exact Online by exposing them as relational SQL models.
This server wraps that driver and makes Exact Online data available through a simple MCP interface, so LLMs can retrieve live information by asking natural language questions — no SQL required.
git clone https://github.com/cdatasoftware/exact-online-mcp-server-by-cdata.git
cd exact-online-mcp-server-by-cdata
mvn clean install
This creates the JAR file: CDataMCP-jar-with-dependencies.jarlib
folder in the installation directory, typically:
C:\Program Files\CData\CData JDBC Driver for Exact Online\
/Applications/CData JDBC Driver for Exact Online/
java -jar cdata.jdbc.exact.jar --license
Run the command java -jar cdata.jdbc.exact.jar
to open the Connection String utility.
Configure the connection string and click "Test Connection"
Note: If the data sources uses OAuth, you will need to authenticate in your browser.
Once successful, copy the connection string for use later.
.prp
file for your JDBC connection (e.g. exact-online.prp
) using the following properties and format:
Prefix=exact
ServerName=CDataExact
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.exact.jar
DriverClass=cdata.jdbc.exact.ExactDriver
JdbcUrl=jdbc:exact:InitiateOAuth=GETANDREFRESH;
Tables=
Create the config file for Claude Desktop ( claude_desktop_config.json) to add the new MCP server, using the format below. If the file already exists, add the entry to the mcpServers
in the config file.
Windows
{
"mcpServers": {
"{classname_dash}": {
"command": "PATH\\TO\\java.exe",
"args": [
"-jar",
"PATH\\TO\\CDataMCP-jar-with-dependencies.jar",
"PATH\\TO\\exact-online.prp"
]
},
...
}
}
Linux/Mac
{
"mcpServers": {
"{classname_dash}": {
"command": "/PATH/TO/java",
"args": [
"-jar",
"/PATH/TO/CDataMCP-jar-with-dependencies.jar",
"/PATH/TO/exact-online.prp"
]
},
...
}
}
If needed, copy the config file to the appropriate directory (Claude Desktop as the example). Windows
cp C:\PATH\TO\claude_desktop_config.json %APPDATA%\Claude\claude_desktop_config.json
Linux/Mac
cp /PATH/TO/claude_desktop_config.json /Users/{user}/Library/Application\ Support/Claude/claude_desktop_config.json'
Run or refresh your client (Claude Desktop).
Note: You may need to fully exit or quit your Claude Desktop client and re-open it for the MCP Servers to appear.
java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/Salesforce.prp
Note: The server uses
stdio
so can only be used with clients that run on the same machine as the server.
Once the MCP Server is configured, the AI client will be able to use the built-in tools to read, write, update, and delete the underlying data. In general, you do not need to call the tools explicitly. Simply ask the client to answer questions about the underlying data system. For example:
The list of tools available and their descriptions follow:
In the definitions below, {servername}
refers to the name of the MCP Server in the config file (e.g. {classname_dash}
above).
{servername}_get_tables
- Retrieves a list of tables available in the data source. Use the {servername}_get_columns
tool to list available columns on a table. The output of the tool will be returned in CSV format, with the first line containing column headers.{servername}_get_columns
- Retrieves a list of columns for a table. Use the {servername}_get_tables
tool to get a list of available tables. The output of the tool will be returned in CSV format, with the first line containing column headers.{servername}_run_query
- Execute a SQL SELECT queryIf you are scripting out the requests sent to the MCP Server instead of using an AI Client (e.g. Claude), then you can refer to the JSON payload examples below – following the JSON-RPC 2.0 specification - when calling the available tools.
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "source_get_tables",
"arguments": {}
}
}
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "source_get_columns",
"arguments": {
"table": "Account"
}
}
}
{
"jsonrpc": "2.0",
"id": 3,
"method": "tools/call",
"params": {
"name": "source_run_query",
"arguments": {
"sql": "SELECT * FROM [Account] WHERE [IsDeleted] = true"
}
}
}
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Securely access BigQuery datasets with intelligent caching, schema tracking, and query analytics via Supabase integration.
A runtime-configurable MCP server that turns a Supabase project into an AI-compatible tool interface.
An MCP-based database server with support for SQLite, MySQL, PostgreSQL, and MSSQL.
Implement semantic memory layer on top of the Qdrant vector search engine
Provides tools and resources for coding agents to interact with the Gel database, including automatic project configuration for query builders and ORMs.
Allows Claude AI to interact directly with MySQL databases.
Query the Materials Project database using the mp_api client. Requires an MP_API_KEY environment variable.
Official MCP Server from Atlan which enables you to bring the power of metadata to your AI tools
A read-only MCP server for querying live data from various APIs using the CData JDBC Driver for API Driver.
Manages personal knowledge using a local Neo4j container, with data imported from JSON files.