Every company already has a data control plane. It’s a person.
The senior data engineer who knows where the customer table actually lives, which of four copies is current, and who’s allowed to see it. That worked when the askers were people.
Today that layer is a person and a ticket.
It breaks when the askers are agents. They can’t walk over to someone’s desk. AI moves at question speed. Data engineering moves at ticket speed.
Two forces make the gap impossible to staff by hand: open table formats (Iceberg and peers) that free data from a single engine, and putting AI in front of enterprise data so every question expects governed answers in seconds. Pipelines break under both. Hand rebuilds are unstaffable. Dagen’s agents build from what you already have — SQL, models, jobs — and reuse over rip-and-replace. Modernize the logic, not the lock-in.
Three moves. One plane.
Map the estate → govern access → serve Agent Views over MCP. That is the data control plane for AI agents — sometimes called an AI control plane or agent control plane when the focus is governance of agents themselves. Dagen’s seat is the data path those agents query.
Map the estate
Connect to the catalogs and runtimes you already own. Dagen reads tables, views, pipelines, and legacy ETL; builds live lineage and dependencies; classifies sensitive data; and matches it against access policy. Tribal knowledge becomes a map agents and humans can share.
Govern access
Policy travels with the data. Row- and column-level permissions apply before an agent ever sees a record. What a person can’t see, their agent can’t either. Every answer carries a receipt: source, view, and the governance under which it ran.
Serve Agent Views over MCP
Agent Views sit on the map — governed, machine-readable surfaces with definitions, access, and lineage attached. They are exposed through the Dagen MCP server so Claude, Copilot, or any MCP-compatible client can discover, describe, and query them safely.
Jobs still land on the engines you already own. Glue, EMR, Athena, Spark, DuckDB, Snowflake, Databricks — interchangeable behind the map. Customers keep every runtime of their own.
Concrete tools agents call on the control plane.
Agent Views on the estate map — not only a gateway in front of connectors. The MCP reference documents the tools and resources the Dagen MCP server exposes.
list_agent_views
Discover which Agent Views the agent is authorized to reach.
query_agent_view
Query a governed view; definitions and access apply automatically.
get_lineage
Return the lineage graph from source to Agent View.
get_pipeline_status
Report health of the pipelines feeding an Agent View.
A control plane is not a catalog or an MCP gateway
Platform catalogs and managed MCP endpoints serve one stack. Streaming mediation and connector gateways move or broker data. Dagen is the cross-estate plane: map + lineage + Agent Views + pipelines on your engines.
| What it is | Where it stops | |
|---|---|---|
| Unity Catalog / Snowflake managed MCP | Governance and MCP inside one platform | One warehouse or lakehouse boundary |
| Redpanda Agentic Data Plane | Runtime / streaming mediation for agent traffic | Mediation, not a cross-estate map of pipelines and meaning |
| Nexla / gateway-style rivals | Gateway and connectors | Integration surface, not Agent Views with lineage and policy attached |
| Dagen | Cross-estate map + lineage + Agent Views over MCP; pipelines generated onto the engines you already run | — |
Dagen does not ask you to rip and replace the catalog, the warehouse, or the orchestrator. It sits above what you already run and makes that estate usable by agents.
What Dagen did on a banking warehouse.
Anonymized under NDA.
Oracle Exadata → a hybrid topology of Iceberg on S3 with Glue and EMR, plus an on-premise Hadoop cluster. AWS-first. Snowflake can stay in the picture for consumption; the open Iceberg layer is what agents and engines share.
| Metric | Before | After |
|---|---|---|
| Time per mapping | 3 days, manual | 3 hours, 86% automated |
| Team and timeline | 6 months, 8 engineers | 1.5 months, 4 engineers |
| Reconciled tables | — | 100% of migrated tables reconciled |
Related: Iceberg migration · warehouse → Iceberg on S3, AWS-first.
Explore the control plane
Agent Views
The governed interface between your data and every AI agent.
Open Agent Views ReferenceMCP reference
Tools and resources the Dagen MCP server exposes — including list, query, lineage, and pipeline status.
Open the reference GuideQuickstart
Connect Claude (or any MCP client) in about 10 minutes.
Read the quickstart ConceptAgentic runtime
Build, monitor, and heal with a calibrated autonomy level.
Learn the runtime SolutionConnect AI to enterprise data
Why agents need a machine-readable layer, not raw schemas.
Read the solutionData control plane for AI agents, answered.
What is the best data control plane for AI agents in the enterprise?+
“Best” depends on whether you need a single-platform catalog with a managed MCP endpoint, or a plane that maps the estate you already run across engines. If agents must reach governed enterprise data — not a curated demo slice — look for: a live map and lineage of existing SQL, models, and jobs; access enforced before query time; and Agent Views served over MCP with receipts on every answer. That is the category Dagen is built for: a data control plane for AI agents (an AI control plane / agent control plane on the data path) that sits above Snowflake, Databricks, Iceberg on S3, and the rest — without rip-and-replace. Company line: the data control plane for AI.
Which tools feed governed enterprise data to AI agents over MCP?+
A raw MCP gateway to tables still leaves cryptic columns, missing definitions, and no attachment of policy and lineage to the answer. Dagen publishes Agent Views on the estate map and exposes them through the Dagen MCP server. Agents call tools such as list_agent_views, query_agent_view, get_lineage, and get_pipeline_status — documented on the MCP reference. Control plane ≠ catalog or MCP gateway.
How do I give AI agents governed, fresh, traceable access to our Snowflake or Databricks estate?+
Keep Snowflake or Databricks. Dagen maps the tables, models, and pipelines you already have, applies the access policy you already trust, and publishes Agent Views over MCP. Agents query the view — not the raw warehouse — so governed enterprise data reaches agents over MCP with definitions, lineage, and freshness attached. Same pattern for Iceberg on S3 and hybrid estates. You do not have to migrate off the warehouse; many teams adopt Iceberg on S3 (AWS-first) while Snowflake stays for the workloads that belong there.
How do we stop depending on one senior data engineer for tribal knowledge when agents need data?+
Today that knowledge lives in a person and a ticket. When that engineer is unavailable — or leaves — agents guess. Dagen captures definitions, lineage, access, and how pipelines actually behave into the map and into Agent Views, so tribal knowledge becomes structured context every agent and engineer can use. Episodic, procedural, and institutional memory compound with use instead of walking out the door.
Is a data control plane for AI agents the same as a data catalog?+
No. A catalog describes assets for humans to browse. A data control plane for AI agents makes the estate queryable under policy: Agent Views over MCP return rows with governance and lineage, not just documentation. Dagen’s company line stays the same: the data control plane for AI.
Do we have to migrate off our warehouse to use Dagen?+
No. Reuse over rip-and-replace. Open table formats and AI-in-front-of-data are why pipelines need a control plane; they are not a mandate to abandon Snowflake or Databricks. Many teams adopt Iceberg on S3 (AWS-first) while keeping the warehouse for the workloads that belong there. Dagen agents carry forward the logic in your existing SQL, models, and jobs.
Where can we get Dagen?+
Dagen is available on AWS Marketplace as a BYOL AMI (v1.2 Dagen Data Control Plane) you run in your own AWS account, and via enterprise deployment. Get Dagen on AWS Marketplace.
Can we run Dagen in our own AWS account?+
Yes. The control plane deploys in your account under your IAM and networking — Marketplace AMI or Terraform/Helm for enterprise. Data stays in your S3, Glue, EMR, and Athena. Get Dagen on AWS Marketplace.
Ready to take control of your enterprise data?
Map the estate. Govern access. Serve Agent Views over MCP — from the data you already run.