> ## Documentation Index
> Fetch the complete documentation index at: https://docs.particle.pro/llms.txt
> Use this file to discover all available pages before exploring further.

# particle_report_create

> Save a Radar report comparing one to four people, companies, topics or keywords, and get its link.

Save a Radar report in your project: a page comparing one to four people, companies, topics or keywords side by side, with their podcast mentions over time, every mention linked to the minute, and their news coverage. The tool returns the report's id and its link on Radar. Give the user the link: the page is where the report is read and downloaded as a PDF, and the tool does not return the report's data.

Every member of the project's organization can open and edit the report. The tool acts on the single project your credential is scoped to.

Resolve each person, company or topic first with [`particle_entity_resolve`](https://docs.particle.pro/mcp/tools/people/entity-resolve), [`particle_person_resolve`](https://docs.particle.pro/mcp/tools/people/person-resolve) or [`particle_company_resolve`](https://docs.particle.pro/mcp/tools/companies/company-resolve), and pass the slug as `entity`. Use `keyword` for a name with no slug.

## Inputs

| Field | Type | Required | Default | Description |
| - | - | - | - | - |
| `subjects` | array | yes | — | One to four subjects, in display order. Each has exactly one of `entity` (a slug) or `keyword`, and an optional `label`. |
| `subjects[].entity` | string | — | — | Slug of a person, company or topic, from a resolve tool. |
| `subjects[].keyword` | string | — | — | A word or phrase matched against podcast transcripts. |
| `subjects[].label` | string | no | the entity's name, or the keyword | Display name for the subject. |
| `name` | string | no | the subjects, as "A vs B" | Report name, up to 120 characters. |
| `period` | string | no | `3mo` | A number of days or months back (`30d`, `3mo`, `12mo`), or `all`. Set this or `from`/`to`. |
| `from` / `to` | string | no | — | An explicit period, `YYYY-MM-DD`, `to` inclusive. Both are required together. |
| `sources` | array | no | `["podcasts", "news"]` | `podcasts`, `news`, or both. |
| `sort` | string | no | `popularity` | Order of each subject's mention list: `popularity` or `recency`. |
| `episode_cap` | integer | no | `25` | Most episodes listed per subject: `25`, `50` or `100`. |
| `omitted_sections` | array | no | none | Optional sections to leave out: `trend`, `shared`, `news`. |
| `hidden_episodes` | array | no | none | Episode ids to leave out of the mention lists. |

## Output

```markdown theme={"dark"}
## NVIDIA vs AMD
**Link:** [NVIDIA vs AMD](https://radar.particle.pro/reports/5Hq2VbKc8mR1tW9y)
**ID:** `5Hq2VbKc8mR1tW9y`
**Period:** 3mo
**Sources:** podcasts, news
**Sort:** popularity
**Episodes per subject:** 25
**Last edited:** 2026-11-16

### Subjects (2)
- NVIDIA — `company:2kTd8mQ4vX7pL1nB`
- AMD — `company:9Rw3cF6hJ2sK8yZe`
```

Passing `output_format: "json"` returns the report as compact JSON, with `url`, `subjects` and `settings`.

## Example

```text theme={"dark"}
Agent calls: particle_report_create {
  "subjects": [{ "entity": "nvidia" }, { "entity": "amd" }],
  "period": "12mo"
}
```

## Related

* REST equivalent: `POST /v1/projects/{projectId}/reports`.
* Change the report with [`particle_report_update`](https://docs.particle.pro/mcp/tools/reports/report-update); find saved ones with [`particle_report_list`](https://docs.particle.pro/mcp/tools/reports/report-list).
* To answer a coverage question rather than hand over a page, use [`particle_podcast_find_mentions`](https://docs.particle.pro/mcp/tools/podcasts/podcast-find-mentions).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.