> ## Documentation Index
> Fetch the complete documentation index at: https://docs.syrto.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Search companies
> Find Italian companies by sector, location, size, financial filters, or natural language description.
`syrto_search_companies` finds companies matching structured criteria — sector, region, size, employee count, financial metrics, or a natural language description. Unlike [`syrto_find_company`](/mcp/tools/find-company) (which searches by name or tax ID), this tool filters by business characteristics.
If you need the **total count** of matching companies or aggregate statistics (average revenue, median EBITDA, etc.), use [`syrto_aggregate_companies`](/mcp/tools/aggregate-companies) instead — this tool only returns paginated results.
## Use this tool to
* Find companies in a specific sector, region, or size class
* Search by a natural language description of what the company does
* Filter companies by financial metric values (e.g. revenue above a threshold)
**Related tools:** For lookup by company name or tax ID, use [Find company](/mcp/tools/find-company). For aggregate statistics, use [Aggregate companies](/mcp/tools/aggregate-companies).
## Arguments
Company profile filters as a JSON object. All fields are optional:
| Field | Type | Description |
| ------------------------------------------ | ------ | --------------------------------------------------------------------------------------------------------------------------------------------------- |
| `nace` | string | EU NACE sector code. Auto-detects level: section letter (`A`–`U`), division (2 digits, e.g. `"10"`), group (e.g. `"10.1"`), class (e.g. `"10.11"`). |
| `nuts` | string | EU NUTS region code. Auto-detects level: level 1 (3 chars, e.g. `"ITH"`), level 2 (4 chars, e.g. `"ITH3"`), level 3 (5 chars, e.g. `"ITH35"`). |
| `semantic_search` | string | Natural language description to search company profiles (max 500 characters, e.g. `"renewable energy solar panels"`). |
| `age` | object | Company age filter with `min` and/or `max` in years. E.g. `{"min": 5, "max": 20}`. |
| `shareholder_age` | object | Average age of shareholders with `min` and/or `max` in years. E.g. `{"min": 50, "max": 70}`. |
| `beneficial_owner_age` | object | Average age of beneficial owners with `min` and/or `max` in years. E.g. `{"min": 40, "max": 65}`. |
| `executive_officer_age` | object | Average age of executive officers (CEOs, managing directors) with `min` and/or `max` in years. |
| `representation_and_authority_officer_age` | object | Average age of officers with representation and signing authority, with `min` and/or `max` in years. |
| `target_market` | string | One of: `B2B`, `B2C`, `B2G`, `B2B2C`, `B2B2G`, `C2C`, `C2B`, `G2C`, `G2B`. |
| `match_cutoff` | float | Minimum semantic similarity score (0.0–1.0) when using `semantic_search`. Higher = fewer but more relevant matches. |
| `country_code` | string | ISO 3166-1 alpha-2 country code (e.g. `"IT"`). |
**Example:** `'{"nace": "C", "nuts": "ITH3", "age": {"min": 5}, "target_market": "B2B"}'`
Fiscal year for annual data filters. **Required** when `size`, `metric_filters`, `employees`, or `radar` are used, or when sorting by metric.
One or more company size classifications: `"XS"`, `"S"`, `"M"`, `"L"` (e.g. `["S", "M"]`). Requires `year`.
Up to 10 metric value filters. Each object has `slug` (required), `min` (optional), `max` (optional). Requires `year`.
Use [`syrto_search_metric_definitions`](/mcp/tools/metric-definitions) to find valid slugs.
**Example:** `'[{"slug": "revenues_from_sales_and_services", "min": 1000000}]'`
Employee count filter with `min` and/or `max`. At least one is required. Requires `year`.
**Example:** `'{"min": 50, "max": 500}'`
Filter by position on the Syrto Radar plane (0–100 on both axes). Combines via AND with all other filters. At least one of `size`, `efficiency`, or `polygon` is required. Requires `year`.
| Field | Type | Description |
| ------------ | ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `size` | object | Inclusive range on the Radar size axis with `min` and/or `max` (0–100). Distinct from the top-level `size` parameter (XS/S/M/L band). |
| `efficiency` | object | Inclusive range on the Radar efficiency axis with `min` and/or `max` (0–100). |
| `polygon` | object | Arbitrary polygon over the (size, efficiency) plane. Has a `vertices` list of 3–64 points, each `{ "size": 0–100, "efficiency": 0–100 }`. Use axis ranges for rectangles or strips; use the polygon for triangles, L-shapes, or concave regions. |
**Example (rectangle):** `'{"efficiency": {"min": 70}, "size": {"min": 40, "max": 80}}'`
**Example (polygon):** `'{"polygon": {"vertices": [{"size": 0, "efficiency": 70}, {"size": 60, "efficiency": 100}, {"size": 100, "efficiency": 70}]}}'`
Filter by consolidated financial statements. Default: `false` (non-consolidated).
Sort configuration as a JSON object. Fields:
| Field | Type | Description |
| ------------- | ------ | -------------------------------------------------------------------------------------------------------------- |
| `field` | string | `"match_score"` (default, meaningful with `semantic_search`) or `"metric"` (sort by a financial metric value). |
| `direction` | string | `"desc"` (default) or `"asc"`. |
| `metric_slug` | string | Required when `field` is `"metric"`. The metric slug to sort by. |
**Example:** `'{"field": "metric", "metric_slug": "revenues_from_sales_and_services", "direction": "desc"}'`
Cursor for pagination. Pass the `end_cursor` value from a previous response to fetch the next page. Omit for the first page.
At least one filter parameter must be provided. Returns up to 25 results per page — use the `end_cursor` from the response as the `after` parameter to fetch the next page.
## Returns
Whether more results are available beyond the current page.
List of matching companies (up to 25), each with:
* `id` — the `company_id` to pass to other Syrto tools
* `legal_name` — official registered company name
* `tax_id` — Italian tax identifier (`null` if not available)
* `match_score` — semantic similarity score (`float`, only present when `semantic_search` is used)
* `short_description` — brief description of the company's activity (only present when `semantic_search` is used)
* `metrics` — list of metric objects with `name`, `slug`, `value`, `better_when` (only present when `metric_filters` or `sort_by` with `field: "metric"` is used)
Cursor token for fetching the next page. Pass this as the `after` parameter. `null` when there are no more pages.
Context note about data availability and where to find more on syrto.ai.
## Example
**Find large manufacturers in Emilia-Romagna:**
```json theme={null}
{
"anagraphic_filters": "{\"nace\": \"C\", \"nuts\": \"ITH5\"}",
"year": 2023,
"size": ["L"]
}
```
**Result:**
* Filters for NACE section C (manufacturing), NUTS level 2 ITH5 (Emilia-Romagna), size L (large)
* Returns up to 25 companies per page; pass `end_cursor` as `after` to fetch additional pages