Custom actions let the AI agent call external APIs during a conversation. When a user asks “Where is my order?” the agent can call your order-lookup API and return the real answer.
Action types
OpenAPI Import
Manual Configuration
MCP Tools
Import an OpenAPI (Swagger) specification to automatically create actions for each endpoint.Go to Actions
Navigate to Actions in the dashboard sidebar.
Import OpenAPI spec
Click Import OpenAPI and paste your spec URL or upload the JSON/YAML file (max 2 MB, spec body max 500K characters).
Select endpoints
Choose which endpoints to expose to the agent. Each becomes a callable tool.
Create actions one at a time with full control over the request.| Field | Description | Limit |
|---|
| Name | Tool name the agent sees | 100 chars |
| Description | When to use this action | 500 chars |
| URL | Endpoint URL | 2048 chars |
| Method | HTTP method (GET, POST, PUT, DELETE, PATCH) | — |
| Parameters | Named parameters with types and descriptions | Max 20 |
| Body template | JSON template with {{param}} placeholders | 10K chars |
| Headers | Static or dynamic headers | — |
Connect Model Context Protocol (MCP) servers to expose their tools to the agent.The agent container includes a built-in MCP proxy that connects to external MCP servers. Configure the server URL in the dashboard and the proxy discovers available tools automatically.
User tokens
If your API requires user-specific authentication, the widget can forward custom headers to action endpoints via userTokens:
<script>
AgenticTrust.initAsync({
projectId: "proj_your_project_id",
apiUrl: "https://platform.agentictrust.com/api/v1",
apiKey: "lum_pk_your_api_key",
userTokens: {
Authorization: "Bearer user_jwt_here"
}
});
</script>
User tokens are forwarded to action endpoints as-is. Only configure tokens for APIs you trust. Max 10 token keys, each value up to 4096 characters.
Limits
| Resource | Limit |
|---|
| Actions per project | 100 |
| Parameters per action | 20 |
| OpenAPI spec size | 500K chars (2 MB file) |
