Provided by People Data Labs
Look Up One Company by Domain, Name, Website or Ticker (PDL)
Look up one company from its domain, name, website, LinkedIn URL or ticker symbol: the firmographics of the company that owns that domain — its funding rounds and totals, its LinkedIn company page and other social links, and the industry, size and location behind that domain. One company at a time, not a page of companies. Resold per call with no monthly floor. It charges for the closest match, so check likelihood (1 to 10); if name and website disagree, PDL matches the website without a warning.
How to run it
Step 1Set up
Once: paste this into your agent's chat. The Skill installs the CLI and logs in by itself. For an agent that cannot use a shell, connect it over MCP instead.
set up https://glasser.ai/SKILL.md
Show me how to use the People Data Labs endpoint /v5/company/enrich on Glasser.glasser run -p pdl -e '/v5/company/enrich' -i '{"website":"stripe.com","min_likelihood":6}' --endpoint-version 3Uses endpoint version 3. Inspect the current price before running. Install and log in first on Get Started.
Once per Run:
IDEMPOTENCY_KEY=$(uuidgen)Run it, and copy this same block to send it again:
curl -X POST https://api.glasser.ai/v1/runs \
-H "Authorization: Bearer gl_..." \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
-H "Content-Type: application/json" \
-d '{"provider":"pdl","endpoint":"/v5/company/enrich","input":{"website":"stripe.com","min_likelihood":6},"endpoint_version":3}'Reuse the same Idempotency-Key to send it again: the second send is a read of the first Run. A new key is a new Run and a new Charge. Uses endpoint version 3; inspect the current price before running.
Step 2Try a specific example task
When you need to assess a prospect for outreach, you might compare their profile with your criteria and note which details still need verification.
Copy this prompt into your agent to review a profile against your outreach criteria.
Use pdl:/v5/company/enrich on Glasser.
Check this profile against my outreach criteria and flag facts I still need to verify.Endpoint structure
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"name": {
"type": "string",
"minLength": 1
},
"ticker": {
"type": "string",
"minLength": 1
},
"profile": {
"type": "string",
"minLength": 1
},
"website": {
"type": "string",
"minLength": 1
},
"required": {
"type": "string",
"minLength": 1,
"description": "PDL's condition on the returned fields, for example `location AND (website OR linkedin_url)`: a record without them is no match and is not charged. It does not work on a field you also send as input."
},
"min_likelihood": {
"type": "integer",
"maximum": 10,
"minimum": 1,
"description": "PDL's match floor, 1 to 10 (PDL's default is 2): below it PDL returns no match instead of a weaker one, and no match is not charged. PDL suggests 6 or more when accuracy matters; a name alone scores 2 to 5."
}
},
"additionalProperties": false
}{
"website": "stripe.com",
"min_likelihood": 6
}This Endpoint publishes no output schema. You get the Provider's own response body, unchanged — we do not warrant a shape we cannot guarantee.
How pricing works
| Data returned | Charged only when data is returned. | $0.10 |
|---|---|---|
| Provider error | The Provider failed to answer. | $0.00 |
| Timed out | The Run exceeded its time limit. | $0.00 |
| Internal failure | An internal error prevented completion. | $0.00 |