CData Model Context Protocol (MCP) Server Interface for Intacct Access

:warning: Attention: This implementation facilitates read-only interactions with Intacct data. For a comprehensive solution supporting Create, Read, Update, Delete, and Action operations, along with simpler deployment, explore the complimentary CData MCP Server for Intacct (Beta Release).

Primary Objective

This specialized read-only MCP Server was engineered to empower large language models (such as Claude Desktop) with the ability to dynamically query current data residing within Intacct systems. This capability is underpinned by the robust CData JDBC Driver for Intacct.

The CData JDBC Driver abstracts Intacct endpoints, presenting them as conventional relational SQL structures. This server component encapsulates that driver, making Intacct information accessible through the streamlined MCP framework. Consequently, AI agents can retrieve real-time insights by posing inquiries in plain, vernacular language, completely bypassing the need for direct SQL formulation.

Deployment Instructions

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

2. Compile the server artifact: bash mvn clean install

   This procedure yields the executable JAR: CDataMCP-jar-with-dependencies.jar 3. Acquire and install the necessary CData JDBC Connector for Intacct: https://www.cdata.com/drivers/intacct/download/jdbc 4. Activate the CData JDBC Connector License: * Navigate to the lib directory within the driver installation path (e.g., Windows: C:\Program Files\CData\CData JDBC Driver for Intacct\; Mac/Linux: /Applications/CData JDBC Driver for Intacct/) * Execute the licensing utility: java -jar cdata.jdbc.sageintacct.jar --license * Input your credentials (name, email) and the designated license key (or "TRIAL"). 5. Define the Data Source Connection Parameters: * Launch the Connection String configuration utility: java -jar cdata.jdbc.sageintacct.jar

   • Configure the necessary connection string details and validate connectivity by clicking "Test Connection".

     Note: OAuth-based data sources necessitate in-browser user authentication.

   • Upon successful verification, capture the generated connection string for subsequent use.
   • Produce a Configuration Property File (e.g., intacct.prp) detailing the JDBC linkage using the following schema:
   • Prefix: A short designator for the exposed data toolset.
   • ServerName: A unique identifier for this data gateway.
   • ServerVersion: Version designation for the gateway.
   • DriverPath: The absolute file system location of the JDBC driver JAR.
   • DriverClass: The fully qualified name of the JDBC Driver class (e.g., cdata.jdbc.sageintacct.SageIntacctDriver).
   • JdbcUrl: The connection URI generated in the previous step.
   • Tables: Specify table names for restricted access; leave empty to permit access to all schema objects. env Prefix=sageintacct ServerName=CDataSageIntacct ServerVersion=1.0 DriverPath=PATH\TO\cdata.jdbc.sageintacct.jar DriverClass=cdata.jdbc.sageintacct.SageIntacctDriver JdbcUrl=jdbc:sageintacct:InitiateOAuth=GETANDREFRESH; Tables=

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

1. Construct or update the client's configuration file (e.g., claude_desktop_config.json) to incorporate this new MCP gateway definition within the mcpServers object:

   Windows Configuration Snippet

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

   Linux/Mac Configuration Snippet

   { "mcpServers": { "{classname_dash}": { "command": "/PATH/TO/java", "args": [ "-jar", "/PATH/TO/CDataMCP-jar-with-dependencies.jar", "/PATH/TO/intacct.prp" ] }, ... } }

   If necessary, relocate the configuration file to the client's designated location (e.g., for Claude Desktop): Windows Relocation bash cp 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 connected client application to ensure the new data source integration is recognized.

Crucial Note: A complete termination and subsequent relaunch of the AI client process may be required for the MCP Servers to properly register.

Independent Server Execution Mode

To operate the MCP server independently of an integrated client: bash java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/Salesforce.prp

Limitation: The server communicates exclusively via stdio, restricting its use to client applications running on the same host machine as the server process.

Operational Guidance

Upon successful registration of the MCP interface, the consuming AI agent gains the capacity to manipulate the underlying data via associated tools (read, modify, delete, execute actions). Typically, explicit invocation of these tools is unnecessary; instruct the client to resolve queries concerning the linked data repository directly. For instance: * "Determine the variance between finalized sales totals and budgeted figures for the last quarter." * "Tally the volume of unresolved support incidents logged against the 'Phoenix' system." * "Summarize all scheduled appointments for the current business day."

Available Interface Methods & Summaries

Tool definitions below use {servername} to reference the unique identifier assigned in the configuration file (e.g., {classname_dash}). * {servername}_get_tables: Fetches a catalog of accessible data structures. Use {servername}_get_columns subsequently to detail schema attributes. Output adheres to CSV format, including a header row. * {servername}_get_columns: Retrieves the attribute list for a specified data structure. Consult {servername}_get_tables beforehand for the list of available structures. Output adheres to CSV format, including a header row. * {servername}_run_query: Executes a standard SQL SELECT command against the data source.

JSON-RPC Invocation Examples

For scenarios involving scripted interactions with the MCP endpoint, bypassing the high-level AI client interface, utilize the following JSON payloads, compliant with the JSON-RPC 2.0 standard, when calling the defined methods.

Method: intacct_get_tables

{ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "intacct_get_tables", "arguments": {} } }

Method: intacct_get_columns

{ "jsonrpc": "2.0", "id": 2, "method": "tools/call", "params": { "name": "intacct_get_columns", "arguments": { "table": "Account" } } }

Method: intacct_run_query

{ "jsonrpc": "2.0", "id": 3, "method": "tools/call", "params": { "name": "intacct_run_query", "arguments": { "sql": "SELECT * FROM [Account] WHERE [IsDeleted] = true" } } }

Diagnostic Procedures

1. If the CData MCP Server is not visible within the client application interface, ensure the client process has been completely terminated (check Task Manager on Windows or Activity Monitor on macOS).
2. If data retrieval failures occur in the client, meticulously re-verify the connection parameters established in the configuration file (.prp), referencing the connection string generated via the dedicated builder utility.
3. For issues connecting directly to the source system, direct communication with the CData Technical Support Portal is advised.
4. For feedback or technical difficulties related to the MCP server's operation, consider engaging with the CData User Community.

Licensing Terms

This MCP server software is distributed under the permissive MIT License. This grants broad rights for usage, modification, and redistribution, contingent upon adherence to the stipulations outlined in the MIT License file contained within this repository.

Comprehensive Source Connectivity Index

Category	Connectors Available
Financial/Accounting	Access, ADP, Avalara AvaTax, MYOB AccountRight, Paylocity, QuickBooks (Online/Desktop), Reckon, Sage (200, 300, 50 UK, Cloud Accounting, Intacct), Xero, Zuora
CRM/Sales	Act CRM, Bullhorn CRM, Dynamics CRM, Highrise, HubSpot, Insightly, Marketo, NetSuite, Oracle Sales, Pipedrive, Salesforce (Cloud, Financial Service Cloud, Marketing, Pardot), Sugar CRM, Zoho CRM
ERP/Operations	Acumatica, Dynamics 365 (Business Central, GP, NAV), Epicor Kinetic, Odoo, SAP (Ariba, Business One, ByDesign, Fieldglass, HANA, Hybris C4C, Netweaver Gateway, SuccessFactors), Workday
Marketing/Advertising	Act-On, Facebook Ads, Google Ad Manager, Google Ads, LinkedIn Ads, MailChimp, SnapChat Ads, Twitter Ads, YouTube Analytics
Data Warehousing/Lakes	Amazon Athena, Databricks, Greenplum, HDFS, Hive, Impala, JSON, Kafka, Parquet, Presto, Redshift, Snowflake, Spark, Trino, XML
Cloud Storage/Services	Amazon S3, Azure Data Lake Storage, Box, Dropbox, Google Cloud Storage, Google Drive, Microsoft OneDrive, SharePoint
Databases (SQL/NoSQL)	Cassandra, CockroachDB, Couchbase, CouchDB, DB2, Elasticsearch, H2, HSQLDB, MariaDB, MongoDB, MySQL, Oracle, PostgreSQL, SQL Server, Sybase, Teradata
Collaboration/Productivity	Asana, Basecamp, Confluence, DocuSign, Email, FHIR, Freshdesk, GitHub, Gmail, Google Calendar, Jira (Assets, Service Management), Microsoft Planner, Microsoft Teams, Monday.com, OneNote, RSS, Slack, Smartsheet, SurveyMonkey, Trello, Zendesk
Web/APIs	GraphQL, OData, REST, SOAP, Tier1, Twilio
And Many More	Dozens of additional specialized and proprietary connectors are supported via the underlying JDBC framework.

---

== Contextual Information: Business Management Systems == Business administration solutions encompass the entire spectrum of mechanisms, software, governance structures, analytical apparatuses, and established protocols utilized by enterprises to effectively navigate dynamic commercial environments, sustain a competitive footing, and continuously elevate operational effectiveness.

Functional Groupings

These systems can be segmented based on organizational function, addressing areas such as strategic foresight, operational workflow refinement, record-keeping integrity, human resource management, analytical decision support, and performance oversight.

Key functional dimensions generally include: * Mechanisms employed for data capture and verification across all corporate sectors. * Systems dedicated to monitoring and optimizing inherent business workflows. * Platforms centralized for data aggregation and informed executive decision-making.

The rapid pace of technological evolution in recent years has profoundly reshaped this domain, leading to an overwhelming proliferation of available solutions. This complexity challenges executives seeking the optimal technological fit for their specific corporate context. The perpetual drive to minimize expenditures while maximizing revenue, coupled with the necessity to deeply comprehend client requirements and deliver tailored products efficiently, fuels this dynamic landscape. Consequently, leadership must adopt a strategic, long-term perspective on tool acquisition and integration, moving beyond merely adopting the newest trending technology. Solutions must be judiciously chosen and subsequently customized to align perfectly with organizational imperatives, rather than attempting to force organizational processes to conform to off-the-shelf software defaults.

Prevalent Methodologies (circa 2013 Benchmarks)

Surveys, such as one conducted by Bain & Company in 2013, indicate global patterns in the deployment of management tools, reflecting regional economic conditions and specific organizational needs. High-ranking strategies included: * Formalized Strategic Trajectory Setting * Client Relationship Nurturing Systems (CRM) * Instruments for Gauging Personnel Commitment * Competitive Benchmarking Exercises * Integrated Performance Measurement Frameworks (Balanced Scorecard) * Identification of Core Organizational Capabilities * Strategic Divestiture/External Sourcing (Outsourcing) * Structured Organizational Transition Programs (Change Management) * Logistics and Resource Flow Optimization (Supply Chain Management) * Articulation of Organizational Purpose and Future State Vision * Analysis of Customer Demographics for Targeting * Comprehensive Quality Assurance Regimes (TQM)

Enterprise Software Applications

Computer programs or integrated suites used by personnel to execute diverse commercial functions are categorized as business software. These applications are engineered to enhance productivity metrics, quantify performance outcomes, and execute complex tasks with high fidelity. The lineage traces from foundational Management Information Systems (MIS) to expansive Enterprise Resource Planning (ERP) platforms, subsequently incorporating Customer Relationship Management (CRM) modules, culminating in today's prevalent cloud-native business management ecosystems. While IT investment demonstrably correlates with organizational success, two factors critically amplify this value proposition: the efficacy of the system's implementation and the careful selection and subsequent tailoring of the chosen tools.