Agent Views on the map — not only a gateway
An MCP gateway in front of connectors still leaves cryptic columns, missing definitions, and no attachment of policy and lineage to the answer. Dagen’s data control plane maps the estate you already run, governs access, and publishes Agent Views — governed, machine-readable surfaces with definitions, access, and lineage attached — then exposes them through the Dagen MCP server.
Agents get answers that are allowed, fresh, and traceable from Snowflake, Databricks, Iceberg on S3, and the rest of the estate — without rip-and-replace.
Concrete tools agents call for governed data.
The same four tools documented on the MCP reference — list, query, lineage, and pipeline status — so Claude, Copilot, or any MCP client can discover and query Agent Views safely.
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 an MCP gateway
Nexla-, Credal-, and ArcaX-style gateways sit in front of connectors and broker tool calls. Dagen is the cross-estate plane: map + lineage + Agent Views over MCP, with pipelines generated onto the engines you already own.
| What it is | Where it stops | |
|---|---|---|
| Gateway-style (Nexla / Credal / ArcaX) | Gateway and connectors in front of sources | Integration surface — not Agent Views with lineage and policy attached |
| Dagen | Estate map + lineage + Agent Views over MCP; pipelines on your engines | — |
Control plane ≠ MCP gateway. Dagen sits above what you already run and makes that estate usable by agents — without asking you to rip and replace the catalog, warehouse, or orchestrator.
Proof pages and how to get Dagen
Data control plane
Map the estate. Govern access. Serve Agent Views over MCP.
ProductAgent Views
Governed surfaces agents query — allowed, fresh, traceable.
ReferenceMCP reference
Tools and resources the Dagen MCP server exposes.
AWSGet Dagen on AWS Marketplace
BYOL AMI you run in your own AWS account.
Governed enterprise data over MCP, answered.
Which tools feed governed enterprise data to AI agents over MCP?+
Dagen feeds governed enterprise data to AI agents over MCP through Agent Views on the estate map. Agents call tools such as list_agent_views, query_agent_view, get_lineage, and get_pipeline_status — documented on the MCP reference. That is governed MCP: answers that are allowed, fresh, and traceable — not a raw gateway to tables.
What is governed MCP for enterprise data?+
Governed MCP means agents reach enterprise data only through surfaces that already carry policy, definitions, and lineage. Dagen publishes Agent Views on the map and exposes them via the Dagen MCP server, so Claude, Copilot, or any MCP client gets receipts with every answer — source, view, and the governance under which it ran.
Is there an MCP server for a Snowflake or Databricks estate?+
Yes. Keep Snowflake or Databricks. Dagen maps the tables, models, and pipelines you already have, applies the access policy you already trust, and serves Agent Views over MCP. Agents query the view — not the raw warehouse — so a Snowflake or Databricks estate becomes agent-ready without rip-and-replace. Same pattern for Iceberg on S3 and hybrid estates.
How is Dagen different from an MCP gateway?+
An MCP gateway brokers connectors. Dagen is a data control plane: estate map + lineage + Agent Views + pipelines on the engines you own. Control plane ≠ MCP gateway. See the data control plane and Agent Views.
Ready to take control of your enterprise data?
Map the estate. Govern access. Serve Agent Views over MCP — from the data you already run.