Getting Started

This walkthrough takes you from an empty tenant to a completed workflow run. Everything below can be done in the Agentfleet app at agentfleet.co.za or via the REST API.

Prerequisites

• An Agentfleet account with the relevant admin roles (resource, step, workflow, agent administration).
• An MCP server you want to orchestrate against (its base URL and path, e.g. https://api.example.com + /mcp).
• A configured model provider with at least one active model.

1. Register a resource

A resource is an MCP server the platform can call.

1. Go to Resources → Create.
2. Enter a name, description, the Base URL, and the Path (e.g. /mcp).
3. Save. Agentfleet automatically registers the resource with the identity provider and binds its audience — tokens issued for this resource are valid only there.

2. Import its tools

1. Open the resource and choose Import tools.
2. Agentfleet discovers the tools the MCP server advertises and registers each one, including its OAuth scope.
3. Re-import at any time to refresh tool schemas.

PDP-filtered listings

Some MCP servers filter their tool listing per caller. If expected tools are missing after an import, the importing session may lack the scopes needed to see them — import with a suitably privileged principal.

3. Create an agent

1. Go to Agents → Create and give the agent a name, description, and model.
2. Agentfleet registers the agent in the identity provider as a delegated agent with its own confidential client and a per-agent signing key. No client secrets are created or stored — the agent authenticates with short-lived signed assertions.

4. Define steps

A step is a reusable unit of work: a natural-language instruction plus exactly one tool.

1. Go to Steps → Create.
2. Write the instruction — what the step should accomplish and what to return. Be explicit about the success condition; the instruction is the model's contract.
3. Select the tool the step uses.

Example instruction: "Call MatchAdvisor with the candidate FSP number and name from the run inputs. Return the match verdict and its supporting evidence."

5. Compose a workflow

1. Go to Workflows → Create, name and describe it.
2. Add steps in execution order.
3. Activate the workflow — only active workflows can run.

6. Run it

1. Open the workflow and choose Run.
2. Pick the agent that will execute it.
3. Optionally add initial context — key/value inputs visible to the first step. Two keys are reserved: task_id and purpose, which are stamped into every step's delegated token as claims.
4. Queue the run. It executes in the background; track it in the run inspector.

7. Inspect the results

Open the run to see:

• State — Running, Completed, Failed (with reason), or Cancelled.
• Context — every input and every promoted output (toolResult_<n>, modelResponse_<n>) with provenance.
• Summary — steps completed, total tokens, average model latency.
• Per-step detail — each model call (input/output, tokens, latency, round) and each tool call.

Next steps

• Understand the identity model — what the delegated token carries and why.
• Learn the reserved run inputs for task- and purpose-bound sessions.
• Automate the workflow — fire it on a schedule or on an inbound event instead of by hand.
• Guard it with evals — score the workflow against expected cases and catch regressions.
• Explore the REST API to queue runs programmatically.