Skip to content

MetaKarta 12.0 Features & Roadmap

Important License Limitation Disclaimer

Note that some of the features detailed in these release changes may not apply and/or be available for the particular edition/version you are using.

Fall 26 | General Availability scheduled for 09/22/2026

New User Experience

The fully redesigned user experience is optimized for how you work: modern look and feel, consolidated navigation, larger workspace, updated platform and vendor-specific iconography, and harmonized dialog boxes, panels, and object browsers.

Ask MetaKarta

Ask MetaKarta is a conversational experience within the MetaKarta platform, integrated with your preferred LLM provider, including Anthropic, Google, Ollama, OpenAI, and Azure OpenAI. Ask natural-language questions about the metadata estate, lineage, impact analysis, catalog entries, and semantic definitions, then receive an answer resolved against the governed metamodel. Answers include direct links for deeper exploration.

Highlights

Use cases

  • BI Metric Consistency
  • Data & BI Platform Migration
  • Impact & Root Cause Analysis
  • Audit & Compliance

Native MetaKarta MCP Server Support for Agentic AI

MetaKarta’s Model Context Protocol (MCP) server for Metadata Management tools, resources, and prompts delivers governed metadata to external AI agents via the industry-standard for Agentic AI. It returns the metadata evidence behind every response and respects the permissions already in place, so an agent only surfaces what its user is authorized to see.

Highlights

Use cases

  • AI Context & Governance

MetaKarta Semantic Hub

Semantic Hub is a new MetaKarta capability for organizations to define semantic models, link them to ontology, and maintain integrity with your business vocabulary. Teams can compile and deploy models as native semantic artifacts into databases and BI platforms before any query runs. AI agents consume the same verified context, ensuring the same answers regardless of what’s issuing the query.

Use cases

  • BI Metric Consistency
  • Data & BI Platform Migration
  • Metadata Tool Consolidation
  • AI Context & Governance

Semantic Generation from Standards, Databases, and BI Tools

Import and define semantic models from existing databases and BI platforms, both legacy and modern self-service, instead of starting from scratch.

Database Platforms

  • Support platforms include Oracle, Snowflake, Databricks, SAP HANA, and more.

  • Role-Playing Dimension Resolution - Detect a single dimension table joined to the same fact multiple times, such as a date table serving order date, ship date, and delivery date, and generate uniquely named, aliased copies for each. No manual aliasing, no ambiguous join paths.

  • Self-Join Flattening - Resolve self-referencing tables, like an employee table where manager ID points back to the same table, into one level of parent/child indirection. The hierarchy becomes queryable without infinite recursion.
  • Before/After Schema Comparison - Toggle between the raw, as-imported schema and the cleaned, flattened, aliased version to see exactly what changed.
  • Relationship Detection Beyond Keys - Follow documented relationships from ER diagrams and infer relationships already established in BI tool joins. Inferred joins are marked visually and flagged for review before anything’s finalized, so nothing gets assumed silently.
  • Incremental Catalog Merge - Import into an existing semantic catalog instead of starting over. A merge view shows the base catalog, the incoming import, and the merged result side by side as a tree, with a YAML diff and a problems list surfacing conflicts before it is applied.
Legacy BI Tools

The most advanced complex semantic models and metrics can be reverse engineered from popular enterprise analytics tools. These legacy BI tools are typically used for large, enterprise-wide data warehouses (Finance, ERP, Compliance, Audit and Reporting), or as part of packaged business applications for specific vertical markets (Finance, Healthcare, etc.). Supported legacy BI tool migration sources include MicroStrategy, SAP BusinessObjects Universe/UNX, IBM Cognos FM, Oracle OBIEE.

Modern Self-Service BI Tools

Modern self-service BI tools such as the popular Microsoft Power BI and Salesforce Tableau have dominated the analytics reporting market. They also generate a massive BI report sprawl, creating conflicting metrics across reports. Self-service BI semantic models can be migrated with accurate metric expression conversion. Semantic reconciliation can then identify and resolve conflicting metrics.

Semantic Modeling and Reconciliation

  • Semantic Modeling - Design semantic models visually or as code using the Semantic Model Editor, with synchronized diagram and script views.
  • Semantic Model Catalog - Centrally organize, version, and govern semantic models and reusable business logic across the enterprise.
  • Semantic Hub Language (SHL) - Define semantic models in YAML with an open-source language that gets compiled into native formats for multiple platforms.
  • Expanded Metric Types - Build Simple, Custom, Filtered, Level of Detail, Time Offset, Window, and Ratio metrics with corresponding properties, matching the calculation types used in the BI tools you’re migrating from.
  • Cloning - Create a copy of datasets, dimensions, facts, and metrics within your model, applying a prefix or suffix to all names and aliasing without recreating everything manually.
  • Semantic Model Testing - Select dimensions and metrics from the model you designed and run the query against the live data source to verify the query result with the expected result, all before the model is compiled and deployed.
  • Semantic Reconciliation - Compare, deduplicate, merge, and reconcile semantic models to eliminate conflicting definitions and logic.
  • Expression Conversion - Automatically translate calculations and expressions between database and BI platform languages using built-in MetaKarta translation technology or AI-assisted as needed.

Semantic Compiler, Continuous Deployment, and Governance

  • Pre-Compilation Testing - Detect and resolve modeling errors, dependency issues, and platform compatibility problems.
  • Security Policies - Define security once and compile native row-level and platform-specific access controls across target systems.
  • Native Semantic Compilation - Compile and deploy semantic models as native database and BI artifacts without proprietary runtime dependencies.
  • Performance Orchestration - Optimize performance by orchestrating native caching, materialization, and platform-specific optimization strategies.
  • Git & CI-CD Integration - Manage semantic models with version control, branching, code review, and automated deployment pipelines.
  • Vendor-Neutral Deployment - One semantic model compiles into native artifacts across data and BI platforms, from legacy to modern and on-premises to cloud. Add and remove new databases or BI targets to support team tool preferences without redefining a single metric.
  • One Model, Every Consumer - A dashboard, an AI agent, and an ad-hoc SQL query all resolve from the same unified model.
  • Adaptable Compilation - As vendors build out their native semantic capabilities, recompile existing models with updated functionality. The modeling work already done doesn’t get thrown out every time a vendor ships a new feature, keeping you future-ready.

Semantic Binding to Glossary-Based Ontology

Ontology Modeling is a new modeling feature based on Glossary modeling. It manages business meaning and delivers context to Semantic Models in Semantic Hub. Organizations can define business entities, relationships, and hierarchies as a governed ontology model, then bind the ontology model to the physical tables, columns, and metrics that implement it in the shared metadata repository.

Highlights

  • Ontology Model - Define entities, relationships, and hierarchies in the new custom model type.
  • Semantic Mapping & Binding - Link business vocabulary terms to the semantic model and physical assets for end-to-end lineage.
  • AI-Generated Data Documentation - Add descriptions to tables in a semantic model using your preferred LLM provider, including Anthropic, Google, Ollama, OpenAI, and Azure OpenAI, which compile into the native artifacts.
  • Ontology Forward-Engineering - Define semantic links from business vocabulary terms to the semantic model metrics that implement them (Text-to-SQL).

Use cases

  • AI Context & Governance
  • Audit & Compliance

Semantic Context MCP Server for Agentic AI

MetaKarta’s MCP server for Semantic Hub tools, resources, and prompts delivers curated context to external AI agents via the industry-standard for Agentic AI. It returns the metadata evidence behind every response and respects the permissions already in place, so an agent only surfaces what its user is authorized to see.

Highlights

  • Semantic Hub MCP Tools, Resources, and Prompts - Delivers curated context from governed, compiled semantic models and the linked ontology. Agents receive canonical definitions with their business vocabulary already wired in, and generate deterministic queries against the warehouse. Context Sandbox validates through this MCP server.
  • Per-User Access Tokens - Generate a user-level access token to authenticate and authorize their LLM or agent against the MetaKarta MCP server. Permissions follow the individual, so agent access mirrors exactly what that person is already authorized to see.

Semantic Context AI Evals and Sandboxing

Context Sandbox is an environment that lets teams validate whether an ontology or semantic definition returns the correct answer when consumed by an LLM. It is verified against live data rather than assumed from the model alone.

Highlights

  • Testing Environment - Run representative business questions against governed context.
  • Answer Evaluation - Compare outputs with expected results or approved reference answers.
  • Binding Validation - Confirm ontology concepts resolve to the correct lineage, tables, columns, metrics.
  • Grounding Inspection - See which definitions, relationships, or physical assets supported the result.

Use cases

  • AI Context & Governance
  • Audit & Compliance

Other MetaKarta Improvements and New Features

  • Manage > Users: Max User Sessions

Spring 27 | Update Release scheduled for 03/15/2027

MetaKarta Semantic Hub

Semantic Generation from Standards, Databases, and BI Tools

Semantic Modeling Standards
  • Apache Ossie (incubating), formerly Open Semantic Interchange (OSI).
  • Microsoft DAX (Data Analysis Expressions) is the native formula and query programming language used in Microsoft Power BI, Analysis Services, and Excel Power Pivot.
Semantic Modeling Tools
  • Semantic Layer tools such as dbt Labs, AtScale, Cube.

Semantic Binding to Glossary-Based Ontology

  • Ontology Generation from unstructured files, such as Word documents and PDF files.

Semantic Context AI Evals and Sandboxing

  • Conversational BI testing.
  • Deep Analysis with Multi-step Agents.

[ask-a-business-oriented-question]: