Build Agentic AI foundations

MCP is an open standard designed to create a consistent, universal language for AI agents and Large Language Models (LLMs) to communicate with external systems. Its primary purpose is to allow an AI agent or an AI assistant to securely connect with an application (eg. data catalog), data sources, and tools. This ensures that the AI’s responses and actions are not just based on its general training data, but are grounded in the specific, real-time context of your organization’s data landscape.

The Actian MCP Server is our implementation of the open MCP standard. It functions as a secure bridge connecting your AI tools (like Claude or Microsoft Copilot) directly to the rich, real-time metadata within the Actian Data Intelligence Platform. It allows both human users and AI agents to conversationally query your data catalog to discover data assets, understand business terminology, and map complex data relationships without ever leaving their workflow.

Our key differentiators are rooted in our platform’s architecture and our strategic approach:

• Knowledge Graph Foundation: Actian’s Data Intelligence Platform is built on a native knowledge graph from the ground up. This allows our MCP Server to deliver a superior and more accurate understanding of complex data relationships and semantic meanings compared to platforms that are not Knowledge Graph-native. This results in a higher-quality context for your AI.
• Focused, High-Value Tools: Actian’s focus is on a curated set of high-impact MCP tools that solve the most critical challenges in data discovery and understanding. This approach delivers tangible results faster and avoids the complexity of an overly broad toolset.
• Commitment to Open Standards: By building on the open MCP standard, we ensure our server is designed for interoperability and can evolve with the rapidly changing AI ecosystem, protecting you from vendor lock-in.

Context engineering is the critical process of providing AI with the right information at the right time to ensure its actions are accurate and reliable. The Actian MCP Server is purpose-built for this:

• It Grounds AI in Reality: By connecting directly to the data catalog, it prevents AI from “hallucinating” or using incorrect data.
• It Teaches AI Your Business Language: With Actian MCP, an analyst can use AI to understand precisely what their organizational definition of a specific business term is before attempting to analyze it.
• It Shows AI Where to Look: It assists users in locating the precise, certified dataset they need to query for accurate insights.

Essentially, the Actian MCP Server turns your passive data catalog into an active, queryable brain that your AI agents can consult before they take any action.

The Actian MCP Server is designed to connect with a variety of AI assistants and automation frameworks. Confirmed compatible tools include:

• Claude
• Cursor
• Windsurf
• Microsoft Copilot Studio
• ChatGPT

Because our server is based on the open MCP standard, we anticipate this list of compatible tools will continue to grow as the ecosystem evolves.

The Actian MCP Server provides a set of tools that allow you or your AI agent to perform specific actions against your metadata catalog:

• Look Up Official Definitions: Use the find_glossary_definition tool to retrieve the exact, approved definition for any business term stored in your glossary.
• Find Data Behind a Concept: Use the get_glossary_implementations tool to locate all the physical data assets (tables, files, etc.) that are linked to a specific business concept.
• Map Data Relationships: Use the get_dataset_data_model tool to instantly understand how a dataset is connected to others, including its specific fields and relational dependencies.
• Discover Related Ideas: Use the semantic_search_glossary tool to perform an AI-powered search that finds conceptually similar business terms, even if they don’t share the same keywords.