Spring AI MCP Intacct Query STDIO Server
@james-wang-sage
About Spring AI MCP Intacct Query STDIO Server
No overview available yet
Basic information
Config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Spring AI MCP Intacct Query STDIO Server?
A Spring Boot starter that implements a Model Context Protocol (MCP) server to query Sage Intacct objects and retrieve their model definitions using the Intacct Core API. It uses STDIO transport and is intended for developers building AI‑assisted financial or ERP workflows with Spring AI.
How to use Spring AI MCP Intacct Query STDIO Server?
Build the JAR with ./mvnw clean install -DskipTests. The server typically starts automatically via an MCP client; alternatively, run it standalone with Java system properties for Intacct OAuth2 credentials (e.g., -Dintacct.client-id=…). The client can then call the MCP tools executeQuery, getModelDefinition, and listAvailableModels.
Key features of Spring AI MCP Intacct Query STDIO Server
- Query Sage Intacct objects with flexible filters, pagination, and field selection.
- Retrieve detailed model definitions for Intacct resources.
- List all available Intacct resource model summaries.
- Supports rich filter operators:
$eq,$ne,$gt,$lt,$in,$contains, etc. - OAuth2 authentication with automatic token caching (Caffeine).
- STDIO transport for integration with Claude Desktop or other MCP clients.
Use cases of Spring AI MCP Intacct Query STDIO Server
- AI assistant queries active vendors in accounts‑payable.
- Retrieve field-level metadata for an Intacct object before building a dynamic form.
- List all available Intacct resources for documentation or tool selection.
- Filter and sort vendor records by due amounts or status.
FAQ from Spring AI MCP Intacct Query STDIO Server
What are the prerequisites?
Java 17 or later, Maven 3.6+, a Sage Intacct account with API access, and OAuth2 credentials (client ID, client secret, username, password). Optionally, Claude Desktop for AI assistant integration.
How does authentication work?
The server requires OAuth2 credentials configured via system properties, application properties, or environment variables (intacct.client-id, intacct.client-secret, intacct.username, intacct.password). Access tokens are cached using Caffeine with a configurable TTL (default 55 minutes) and refreshed automatically.
What transport does the server use?
Only STDIO transport is implemented. The server is not a web application (spring.main.web-application-type=none) and is typically launched by the MCP client.
Where does the data come from?
All data is retrieved from the live Sage Intacct API using the base URL https://partner.intacct.com/ia3/api/v1-beta2. The server does not store any data locally.
What tools are available?
Three MCP tools: executeQuery (flexible object query with filters/pagination), getModelDefinition (retrieve object schema and constraints), and listAvailableModels (list all available Intacct resource summaries).
More Other MCP servers
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
Mobile Mcp
mobile-nextModel Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices)
Reactive Resume
amruthpillaiA one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
Blender
ahujasidOpen-source MCP to use Blender with any LLM
ACI: Open-Source Infra to Power Unified MCP Servers
aipotheosis-labsACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.
Comments