"Proof-of-Concept Examples for Multi-Component Processes (Model Context Protocol)" matching MCP servers:

Enables querying Odoo's model registry (fields, inheritance, methods) without a database connection by loading the registry in-memory.

A proof of concept MCP server for Apache OFBiz

Reference MCP server for OCL, an open standard giving AI agents structured, scoped business meaning for Odoo data. Serves published example context packs via get_context, resolve_noun, and explain_field (stdio, Python, Apache-2.0).

Enables users to ask natural-language questions about live 1C:Enterprise data and receive answers from read-only OData sources, covering sales, inventory, items, and counterparties; supports direct connections or an SSH tunnel for IP-allowlisted installations.

MCP server giving Claude (and any MCP-compatible client) live access to SAP systems via ADT for reading, searching, editing, and activating ABAP objects.

A bridge that allows AI agents to access and manipulate Odoo ERP data through a standardized Model Context Protocol interface, supporting partner information, accounting data, financial records reconciliation, and invoice queries.

Enables AI assistants to interact with Odoo ERP systems, letting them search, create, update, and delete business records, run aggregations, invoke business workflow methods, and fetch binary attachments through natural language. It supports API key or username/password authentication, smart field selection, pagination, and multi-language responses.

Enables a single authenticated MCP endpoint to resolve users to the correct tenant, role, permissions, and tenant-specific backend integration, with support for shared, individual, and hybrid identity modes.

Enables AI assistants to securely access and interact with Odoo data through natural language, supporting full CRUD operations, OAuth 2.1 and API key authentication, and granular per-model permissions.

This MCP server enables users to ask natural-language questions about their QuickBooks Online company and receive answers from its live data, with read-only access guaranteed by construction. It runs entirely locally, using tools for receivables, payables, profit/loss, balance sheet, and custom queries.

An MCP server that lets AI models interact with Oracle Fusion Cloud HCM across its entire REST surface. It uses generic, schema-aware tools to dynamically discover licensed modules and resources without per-endpoint code.

Open-source TallyPrime MCP server for Claude Desktop: reads your books, proposes vouchers from bank statement PDFs, and posts only if you turn posting on and approve each voucher. Windows x64 and Apple Silicon Mac.

Enables AI-powered manufacturing operations analysis and automated report generation from SAP DMC, with direct delivery to MS Teams.

Enables employees, approvers, and admins to register and manage time, view balances, cases, employees, and planning through Visma Intempus, with per-user scoping and fail-closed identity.

Provides complete MCP access to Wave Accounting, enabling AI assistants to manage invoices, payments, customers, and bookkeeping via natural language.

A version-agnostic MCP server for Odoo that enables AI agents to interact with any Odoo app's data, schema, and source code, supporting tasks like data CRUD, schema mapping, code analysis, and feature implementation.

Exposes SAP OData v4 actions as AI-callable tools, enabling natural language scheduling of background jobs.

Enables AI clients to securely access and query Microsoft Dynamics 365 data through natural language, supporting data analysis, reporting, and business workflows.

Enables an MCP client such as Claude Code to run financial reports, query records, and create, update, void, delete, deactivate, email, or attach records in a company's QuickBooks Online books through the Accounting API. It runs locally over stdio with read and write tools separated, dry-run previews, an optional read-only mode, and a local audit log so the owner stays in control of every change.

MCP server for querying employee data via tools like get_employees and get_employee_by_id. Serves as a proof-of-concept for integrating Pega applications with AI agents.