Skip to main content
Open source Agent presets save a model, instructions, tools, skills, and MCP integrations under a slug. Open Agents from the workspace navigation to create one, then run it from a workflow with ai.preset_agent. Agents page

​
Configure a preset

Click Create new, name the preset, and write instructions in the editor. Use the Tools tab to select the model, allowed Tracecat actions, and MCP integrations, and the Skills tab to attach published skills. Agent preset tools

​
Where tools come from

Three sources on the preset side make up what the agent can call:
  • Registry actions on the preset, chosen in the Tools tab. The usual home for actions only this agent needs.
  • MCP integrations attached to the preset, also in the Tools tab. An MCP integration reaches a preset directly and does not need to go through a skill.
  • A skill’s metadata.tools, which takes registry actions and MCP references alike. Tools declared here travel with the skill’s instructions, so a group several agents reuse stays in one place.
The effective tool set is the union of the three. A namespaces restriction on the preset filters the registry actions in that set; MCP tools are not filtered by it. A workflow run can swap one piece out. The actions input on the ai.preset_agent action replaces the preset’s registry actions for that run instead of adding to them, so registry actions a skill contributed are dropped for the run. MCP tools stay either way, and an empty list is ignored. It is handy for running a preset with a different tool set in a test or an eval. Leave output_type unset unless you specifically need structured output for a downstream step.

​
Availability

Open source includes presets, skills, secrets and variables in preset instructions, and the MCP catalog connectors. Enterprise Edition Enterprise adds:
  • Agent folders and tags to organize the Agents page.
  • tool_approvals and the agent inbox to review tool calls before they run.
  • @ agent mentions in workspace chat and case comments.
  • See AI agent for the ai.preset_agent inputs and examples.
  • See Skills to attach reusable instructions and files to a preset.
  • See MCP servers to connect servers a preset can call.