Datris.ai Launches the First Data Platform Built Around MCP as Open Source

Datris Platform — the first AI agent-native, open-source data platform with 30+ MCP tools

Open-source platform with 30+ MCP tools lets AI agents autonomously create pipelines, query databases, search vector stores, and operate the full data lifecycle

We built the MCP server first and made everything accessible through it. Agents are native operators, not second-class citizens.”

— Todd Fearn, Founder and CEO, Datris.ai

NEW YORK, NY, UNITED STATES, March 31, 2026 /EINPresswire.com/ -- Datris.ai today announced the open-source release of Datris Platform, the first data platform where the Model Context Protocol (MCP) is the primary interface. Rather than adding AI capabilities to a traditional data platform, Datris was designed from the ground up for AI agents to operate as first-class pipeline operators alongside humans.

The platform includes a native MCP server with over 30 tools spanning pipeline creation, data ingestion, validation, transformation, database queries, vector database search, natural language SQL, RAG-powered question answering, data profiling, error diagnosis, and metadata discovery. Any MCP-compatible agent — Claude, Cursor, or custom frameworks — can operate the full data lifecycle without custom integration code.

"We built the MCP server first and made everything accessible through it," said Todd Fearn, Founder and CEO of Datris.ai. "Most platforms bolt on an AI layer after the fact. We wanted agents to be native operators, not second-class citizens."

Key Capabilities

MCP-Native (30+ Tools) - Create pipelines from sample data in a single call with automatic schema detection - Validate and transform data using plain English instructions - Query PostgreSQL and MongoDB; natural language SQL generation and execution - Semantic search across five vector databases: Qdrant, Weaviate, Milvus, Chroma, pgvector - Full RAG pipeline — document extraction, chunking, embedding, and search - Data profiling, error diagnosis, metadata discovery across all backends

Datris CLI - One-liner data pipelines from the terminal

Example command: datris ingest trades.csv --dest postgres --ai-validate "all prices must be positive and dates must be YYYY-MM-DD"

Full Data Lifecycle - Ingest: CSV, JSON, XML, Excel, PDFs, Word docs, archives, database polling, Kafka streaming - Validate: AI rules (natural language), JSON Schema, XSD - Transform: AI transforms (natural language), destination schema mapping - Route: PostgreSQL, MongoDB, Kafka, ActiveMQ, REST, MinIO (Parquet/ORC), five vector databases — all in parallel

Open-Source Stack - Spring Boot, Docker Compose, MinIO, MongoDB, ActiveMQ, HashiCorp Vault, PostgreSQL - AI providers: Anthropic Claude, OpenAI, or Ollama (fully local, air-gapped) - Single docker compose up -d deploys the full stack - No proprietary dependencies, no vendor lock-in

Example Applications

The release includes several example applications, including Market Macro Agent — a live financial data agent that autonomously operates Datris through MCP to ingest market data, run quality checks, and answer natural language queries in real time.

About the Founder

Todd Fearn brings more than 30 years of financial services technology experience to Datris.ai. His career includes senior engineering and architecture roles at Goldman Sachs, Salomon Brothers, Deutsche Bank, Bridgewater Associates, Credit Suisse, Canada Pension Plan Investment Board, Bank of America, UBS, Citibank, and Freddie Mac, where he designed and delivered trading platforms, enterprise data lakes, real-time pipelines, and mobile applications at scale.

Todd is also a serial entrepreneur, having led several venture-backed technology companies: REV Entertainment, funded by Warner Music, Elektra, and Atlantic Records and recognized as an RIAA technical liaison; KaanBaan/Code360, an XML server software company whose products were adopted by Fortune 500 enterprises; and Chord Corporation, a pioneer in LAN messaging software advertised nationally through PC Magazine and Windows Magazine.

Availability

Datris Platform is available immediately.

GitHub: https://github.com/datris/datris-platform-oss Documentation: https://docs.datris.ai Website: https://datris.ai

Media Contact

Todd Fearn Founder & CEO, Datris.ai

Todd Fearn
Datris.ai
email us here

Legal Disclaimer:

EIN Presswire provides this news content "as is" without warranty of any kind. We do not accept any responsibility or liability for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained in this article. If you have any complaints or copyright issues related to this article, kindly contact the author above.