AI & Agentic Overview
DataZen extends beyond classic data integration into AI and agentic workflows. The same governed pipelines and agent APIs that move and manage data can be exposed to large language models as MCP Tools, while assistants can also author correct SQL CDC from the official language specification.
Three complementary MCP capabilities cover the main scenarios:
| Capability | What it does | npm package |
|---|---|---|
| Pipelines as Tools | Expose Reader or Direct pipelines as MCP Tools, develop and test them in Portal AI Chat, then connect Claude, Hermes, Cursor, and other agents with live pipeline results. | datazen-pipeline-mcp |
| DataZen API Tools | Let agents call the DataZen HTTP API as MCP tools for cloud and self-hosted agents—health, jobs, history, variables, and start/stop/activate operations. | datazen-api-mcp |
| AI-Generated SQL CDC | Give AI assistants first-class access to the SQL CDC language specification so they can list operations, look up syntax, and generate correct scripts instead of guessing. | datazen-sqlcdc |
All three MCP servers are published under the Enzo Unified npm organization. Browse the packages here: npmjs.com/settings/enzounified/packages.
Pipelines as Tools
Turn governed DataZen pipelines into tools an LLM can call. Configure an AI Endpoint, define the MCP
Tool metadata on a Reader or Direct pipeline, validate behavior in Portal AI Chat, then register
datazen-pipeline-mcp in an external agent. Optional DECLARE parameters become tool
inputs. See Pipelines as Tools and
MCP Tool.
DataZen API Tools
Operate the agent control plane from an LLM: ping and status, list jobs, read history and logs, inspect
variables and connection metadata, and start, stop, or activate pipelines. Works for both cloud and
self-hosted deployments via datazen-api-mcp and a Service Token. See
DataZen API Tools.
AI-Generated SQL CDC
Authoring SQL CDC is easier when the assistant knows every operation, option, and canonical example.
datazen-sqlcdc is a local language-spec MCP server (no agent credentials required) that exposes
list_operations, get_operation, and get_examples. See
AI-Generated SQL CDC.
How They Fit Together
- Use AI-Generated SQL CDC while building or refining pipeline scripts.
- Use Pipelines as Tools to expose those pipelines to AI Chat and external agents for governed data access.
- Use DataZen API Tools when the agent must manage or observe the DataZen agent itself.
Many agentic setups combine two or all three packages in the same MCP client configuration.