Find Companies by Criteria · People Data Labs

Describe the company criteria you want to research. Your Agent can express supported conditions as an Elasticsearch query or SQL and choose a batch size. A successful search returns matching company profiles and a total match count; the Agent can organize the received records into a shortlist.

Your AI

Use with your AI

For tasks with several steps, continue in the AI you already use.

CodexClaude CodeCursorWindsurfCline

View instructions

Use Toolmu’s find-companies-people-data-labs, catalog ID 298cace5-1b8a-4527-9c5a-8d9407767ef5, to find company records matching my criteria. Reuse the existing Toolmu connection, or follow https://toolmu.com/SKILL.md if setup is needed. Read get_tool for this exact Tool, check current availability and price, and honor my existing authorization and budget. Clarify missing company criteria and express them using supported fields and values from PDL’s company mapping. Supply either an Elasticsearch query or a SQL statement, never both. Use size for the requested batch limit, from 1 to 100; SQL LIMIT and selected columns are ignored. Read the actual company records and keep the delivered count distinct from total. Organize the requested shortlist as separate Agent work, preserving available identity details and unknown values without inventing contact information or company facts. Retrieve only the batch scope I asked for. For a further authorized batch, keep the original query and use its returned scroll_token; each batch is another request within the available budget. Do not automatically retrieve every match.

Task:
Find [software companies in Canada]. Show up to [10 companies] with their available names, websites, and industries. Tell me how many matches exist in total, but stop after this first list.

Paste into your connected AI's conversation.

Connection guide

Up to 12 credits / call

The final charge is based on confirmed usage. Unused reserved credits return to your available balance.

People Data Labs

Find Companies by Criteria · People Data Labs

You receive

You receive a batch of matching company profiles, which can include names, PDL IDs and other available details. The total match count describes the whole query, rather than only this batch. A continuation token can be used for another batch of the same search. Your Agent can arrange these records into a readable shortlist for your task.

Start with your task

Find [software companies in Canada]. Show up to [10 companies] with their available names, websites, and industries. Tell me how many matches exist in total, but stop after this first list.

What to know

A batch is not the complete set represented by total, and the dataset is not a guarantee of coverage of every company. Profile attributes may be unknown or outdated. Matching your conditions does not independently confirm each company fact or rank the companies by suitability.

Inputs & outputs

Inspect the current inputs, availability, and maximum charge before starting.

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
Company search request`body`	`object`	Optional	Request settings with either query or sql, plus an optional batch size, formatting choices and pagination token. Do not supply query and sql together.
Maximum records in this batch`body.size`anyOf · 1	`integer`	—	Integer from 1 to 100, default 1. Sets the maximum matching records requested for this batch, if they exist; it is not the total match count. Default `1` Minimum `1` Maximum `100`
Elasticsearch company query`body.query`anyOf · 1	`object`	—	Structured Elasticsearch query object using supported company fields and query types. Choose this method instead of sql; use field names and values from PDL’s company mapping.
Readable response indentation`body.pretty`anyOf · 1	`boolean`	—	Whether to add human-readable JSON indentation. Defaults to false; this changes formatting without changing the company records. Default `false`
Title-case company text`body.titlecase`anyOf · 1	`boolean`	—	Whether to display response text in title case. Defaults to false; this is a text-formatting option, not verification of company facts. Default `false`
Next-batch bookmark`body.scroll_token`anyOf · 1	`string`	—	Token from the preceding search response. Keep the original query and use the token to request the next batch; another batch is a separate request.
SQL company query`body.sql`anyOf · 2	`string`	—	SQL string expressing company conditions, such as SELECT * FROM company WHERE ... . Use instead of query. PDL ignores selected columns and SQL LIMIT; use size to control the batch limit.
Maximum records in this batch`body.size`anyOf · 2	`integer`	—	Integer from 1 to 100, default 1. Sets the maximum matching records requested for this batch, if they exist; it is not the total match count. Default `1` Minimum `1` Maximum `100`
Readable response indentation`body.pretty`anyOf · 2	`boolean`	—	Whether to add human-readable JSON indentation. Defaults to false; this changes formatting without changing the company records. Default `false`
Title-case company text`body.titlecase`anyOf · 2	`boolean`	—	Whether to display response text in title case. Defaults to false; this is a text-formatting option, not verification of company facts. Default `false`
Next-batch bookmark`body.scroll_token`anyOf · 2	`string`	—	Token from the preceding search response. Keep the original query and use the token to request the next batch; another batch is a separate request.

View raw JSON

{
  "type": "object",
  "required": [],
  "properties": {
    "body": {
      "anyOf": [
        {
          "type": "object",
          "required": [
            "query"
          ],
          "properties": {
            "size": {
              "type": "integer",
              "default": 1,
              "maximum": 100,
              "minimum": 1
            },
            "query": {
              "type": "object",
              "propertyNames": {
                "type": "string"
              },
              "additionalProperties": {}
            },
            "pretty": {
              "type": "boolean",
              "default": false
            },
            "titlecase": {
              "type": "boolean",
              "default": false
            },
            "scroll_token": {
              "type": "string"
            }
          },
          "additionalProperties": false
        },
        {
          "type": "object",
          "required": [
            "sql"
          ],
          "properties": {
            "sql": {
              "type": "string"
            },
            "size": {
              "type": "integer",
              "default": 1,
              "maximum": 100,
              "minimum": 1
            },
            "pretty": {
              "type": "boolean",
              "default": false
            },
            "titlecase": {
              "type": "boolean",
              "default": false
            },
            "scroll_token": {
              "type": "string"
            }
          },
          "additionalProperties": false
        }
      ],
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "~standard": {
        "vendor": "zod",
        "version": 1,
        "jsonSchema": {}
      }
    }
  },
  "additionalProperties": false
}

Result schema

Output fields have not been documented yet.

Additional notes

Build filters from the supported company mapping. PDL’s input guide accepts term, terms, exists, bool, match, range, match_phrase, wildcard, prefix and match_all queries. It excludes aggregations, boosting and custom scoring, and limits any query array to 100 elements. Queries run without cleaning or preprocessing, so field names and values need to match the source mapping.

SQL is an alternative way to express company conditions, typically SELECT * FROM company WHERE ... . PDL accepts statements that translate to its supported Elasticsearch query types. Selected columns and LIMIT are ignored: size controls the batch limit instead. Its input guide also limits LIKE expressions using % to 20 wildcard terms per request.

Read data as the records received and total as the count matching the entire query. Company profiles can contain null where information is unknown. Neither a large total nor a populated record establishes complete market coverage, current data or that the company is suitable for your purpose. The Agent’s shortlist and comparison are separate interpretations of available records.

For another batch, retain the original query and pass the returned scroll_token as the bookmark. This is a separate request, not an automatic retrieval of all matches. PDL documents that an exhausted result can have a null token, and completion can also be reported without a token. Keep pagination within the requested scope and budget; pretty and titlecase only change presentation.

People Data Labs: company query, SQL and pagination inputs

People Data Labs: company records and total matches

Questions about this tool.

Inputs, results and details to know before running it.

Get connected

total counts all records matching the query, while data contains the batch you received. size limits that batch to at most 1–100 records and defaults to 1. A total count is not evidence that all of those profiles have already been retrieved or independently checked.

Find Companies by Criteria · People Data Labs

Find Companies by Criteria · People Data Labs

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Describe the companies you want

Choose how many to review first

Check the list before making a shortlist

Questions about this tool.

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Describe the companies you want

Choose how many to review first

Check the list before making a shortlist

Questions about this tool.

Why does total exceed the records in this batch?

Can SQL LIMIT or selected columns reduce the response?

How do I request another batch?

Does a query object support any Elasticsearch feature?