Trust your process,
not your agents.

Prefect is an open source workflow orchestration platform for data pipelines and AI agents, and the company behind three products: Prefect for workflow and agent orchestration, Dagster for data orchestration and context, and FastMCP for connecting agents to tools through the Model Context Protocol (MCP). Together they give you control over what an agent knows, what it can do and what it is trying to achieve. Each is open source at the core, with a managed service on top.

Workflow orchestration coordinates the steps of a process: the order they run in, what happens when one fails, and who has to approve what before the work moves on. Prefect does this for Python data pipelines and AI agent workflows, with scheduling, retries, durable execution and human review built into the engine instead of into your code.

An MCP gateway is one governed endpoint between AI clients and your MCP servers. It authenticates every client, authorizes each tool call per agent and role, and logs the result, so agents reach the tools they are allowed to use and nothing else. FastMCP Gateway is the managed MCP gateway and MCP hosting service from the team behind FastMCP.

They answer three different questions about an agent. Dagster handles what it knows: your data and business knowledge, curated into context. FastMCP handles what it can do: which tools and systems each agent may reach, and the record of every call. Prefect handles what its goal is: the workflow that runs the work, checks every result and brings in a person when it should.

No. Each product works on its own and most teams start with one. Data teams usually start with Dagster, teams building MCP servers start with FastMCP, and teams automating workflows or agents start with Prefect. Using them together adds decision lineage: every outcome traces back to the context it used, the tools it called and who approved it.

Three differences do most of the work. Workflows are plain Python functions that can branch, loop, and create tasks at runtime, rather than DAGs declared up front. Durable execution is built into the engine, so retries, state, and crash recovery are not code you write. And with Prefect there is no scheduler for your team to host, upgrade, or page anyone about.

Yes. A Prefect workflow is ordinary Python with two decorators, so any coding agent that writes Python can produce a working flow, add retries, and deploy it without learning a DSL. Your engineers review and own the result, and the same is true for humans: if you can write a Python function, you can ship a Prefect flow.

Yes. Prefect, Dagster and FastMCP are all open source under the Apache 2.0 license, and each managed service runs the same engine rather than a fork. FastMCP 1.0 was folded into the official MCP Python SDK.

Only if you want to. Prefect runs flows on managed compute, so you can start with zero infrastructure. Teams with stricter requirements use the hybrid model instead: lightweight workers inside your environment run your code where your data already lives, while the control plane handles scheduling and visibility. That split is what clears most security reviews.

Prefect acquired Dagster Labs in July 2026, bringing together two leading orchestration products. Nothing changes for users of either product: Dagster keeps its name and open-source license, and no action is required of any customer. The full announcement is at prefect.io/prefect-acquires-dagster.