Reckon

This read-only MCP Server allows you to connect to Reckon data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

java

GitHub Stars

java

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-reckon-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/reckon.prp"
      ]
    }
  }
}

You can query Reckon live data with a lightweight MCP server that exposes Reckon data through a simple MCP interface. This read-only server lets language models ask questions in natural language and receive up-to-date results from Reckon without writing SQL.

How to use

After you start the MCP server, you can interact with it from an MCP client to read data. You do not need to write SQL queries; simply ask questions like, “What is the total revenue by month?” or “Show open Reckon invoices.” The server exposes the Reckon data through built-in tools that retrieve tables, list columns, and run read-only queries. The recommended usage pattern is to start the server and then use your MCP client to ask questions in natural language. If you need to inspect available data structures, you can query the server for the list of tables and columns before asking more complex questions.

To start a local, read-only Reckon MCP server, run the provided runtime command and point it at your Reckon configuration file (reckon.prp). The server runs on the same machine as the client when using stdio.

How to install

Prerequisites you must have installed on your system before starting the MCP server:

Java Runtime Environment (JRE) or JDK 8 or newer
Maven (for building the server) or access to a packaged JAR with dependencies

Follow these step-by-step commands to set up and run the MCP server locally

Additional content

Configuration and run flow to bring up the Reckon MCP server locally are described here in actionable steps. You will create a Reckon property file (reckon.prp) that contains your JDBC driver details and the JDBC URL for Reckon, then run the MCP server with the Java runtime.

Run commands exactly as shown to build, configure, and start the server.

Manual MCP configuration example

{
  "mcpServers": [
    {
      "type": "stdio",
      "name": "reckon",
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/reckon.prp"
      ]
    }
  ]
}

Notes and troubleshooting

If you cannot see the MCP server in your client, ensure you have fully quit and relaunched the client so it can detect new MCP servers. Verify that the reckon.prp file contains a valid JDBC connection string and that the required JAR file paths are correct. If there are issues with the Reckon data source, confirm that the JDBC driver is licensed and properly configured.

If you encounter connection problems, double-check the JDBC URL in reckon.prp and verify that your Reckon data source is reachable from the host running the MCP server.

Available tools

reckon_get_tables

Retrieves a list of tables available in the Reckon data source. Output is CSV with column headers on the first line.

reckon_get_columns

Retrieves a list of columns for a specified table. Output is CSV with column headers on the first line.

reckon_run_query

Executes a SQL SELECT query against the Reckon data source and returns the results.

Built by

VeilStrat

AI signals for GTM teams