Skip to main content
List the alerts in your project, newest first. Read-only. Every MCP request is scoped to one project by your credential, so this lists that project’s alerts — there is no project parameter and no way to reach another project’s alerts. Each entry carries the alert id — feed it into particle_alert_get for full configuration, particle_alert_list_matches for what it has caught, or particle_alert_update / particle_alert_delete to manage it. Results are cursor-paginated.

​
Inputs

FieldTypeRequiredDefaultDescription
limitinteger (1–100)no25Alerts per page.
cursorstringno—Opaque pagination cursor from a previous response’s cursor field.

​
Output

A markdown ## Alerts (N) heading followed by one bullet per alert: Title — \id` · kind · cadence · N entities, with a nested Status:row (active/paused). When more results remain, a trailing paragraph names thecursor` to pass for the next page. When the project has no alerts yet, the output is a single line pointing at particle_alert_create. Sample: 
## Alerts (2)

- OpenAI mentions — `dKxN6Ry2mL9pJ5qW` · ENTITY_MENTION · DAILY · 1 entity
  - **Status:** active
- Competitor watch — `7mPq3Wx9aL2nR5tV` · ENTITY_MENTION · WEEKLY · 4 entities
  - **Status:** paused
Passing output_format: "json" returns alerts, has_more, and cursor as compact JSON.

​
Example

Agent calls: particle_alert_list {}
            → reads an alert's `id` → "dKxN6Ry2mL9pJ5qW"

Agent calls: particle_alert_list_matches { "alert_id": "dKxN6Ry2mL9pJ5qW" }