# io.usefulapi/peopledatalabs (remote · peopledatalabs.usefulapi.io)

Enrich and search people and companies, resolve identities, and enrich IP addresses.

- Trust score: 70/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `peopledatalabs.usefulapi.io`: 70/100 (this document), [markdown](https://verifymcp.io/servers/io-usefulapi-peopledatalabs/peopledatalabs.md), [page](https://verifymcp.io/servers/io-usefulapi-peopledatalabs/peopledatalabs)

## Channel facts

- Endpoint: `https://peopledatalabs.usefulapi.io/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 78/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS not yet verified: we couldn't determine whether a plaintext access path exists.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1918 tokens (~239/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http io-usefulapi-peopledatalabs https://peopledatalabs.usefulapi.io/mcp
```

### Codex

```toml
[mcp_servers.io-usefulapi-peopledatalabs]
url = "https://peopledatalabs.usefulapi.io/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-usefulapi-peopledatalabs": {
      "type": "remote",
      "url": "https://peopledatalabs.usefulapi.io/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-usefulapi-peopledatalabs --url https://peopledatalabs.usefulapi.io/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-usefulapi-peopledatalabs:
    url: "https://peopledatalabs.usefulapi.io/mcp"
```

### Other

```json
{
  "mcpServers": {
    "io-usefulapi-peopledatalabs": {
      "type": "http",
      "url": "https://peopledatalabs.usefulapi.io/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 70, +42)

- [security improvement] Authorization: unverified → pass
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.23

### 2026-08-02 (score 28, +10)

- [security improvement] Transport: fail → pass

### 2026-08-01 (score 18, −51)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.13 → unverified
- [security regression] Authorization: pass → unverified
- [security regression] Transport: pass → fail
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: fail → unverified

### 2026-07-31 (score 69, +3)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 66, −1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 67, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-07-27 (score 66, +54)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 12)

First indexed and scored.

## MCP tools (8)

### `pdl_person_enrich` (~417 tokens)

Enrich a person

Find the single best-matching person profile for a set of identifying attributes (name, email, phone, profile URL, company, etc.). Returns one record plus a likelihood score (1-10), or a 404 'no match' body. Use uniquely-identifying inputs for best results. API: GET /person/enrich.

Input parameters:

- `birth_date` (string): Birth date (yyyy or yyyy-mm-dd).
- `company` (string): Company name, website, or PDL company id the person works at.
- `country` (string): Country name, e.g. 'united states'.
- `email`: Email address, or an array of email addresses.
- `first_name` (string): First / given name.
- `last_name` (string): Last / family name.
- `lid` (string): LinkedIn numerical ID.
- `locality` (string): City / locality, e.g. 'san francisco'.
- `location` (string): Free-text location, e.g. 'San Francisco, CA, USA'.
- `min_likelihood` (integer): Only return a 200 if match confidence >= this (1-10).
- `name` (string): Full name, e.g. 'Sean Thorne'.
- `pdl_id` (string): PDL persistent ID for a person record.
- `phone` (string): Phone number (E.164 or local).
- `postal_code` (string): Postal / ZIP code (assumed US if no country).
- `pretty` (boolean): Pretty-print the JSON response.
- `profile`: Social profile URL(s), e.g. a LinkedIn URL. String or array.
- `region` (string): State / region, e.g. 'california'.
- `required` (string): Only return a match that contains these fields, e.g. 'emails AND mobile_phone'.
- `school` (string): School name or website the person attended.
- `titlecase` (boolean): Titlecase the returned data (default false = lowercase).

### `pdl_person_identify` (~360 tokens)

Identify a person

Given broad, possibly-ambiguous attributes about a person, return up to 20 strongly-related profiles ranked by match score. Sits between enrich (1:1) and search (open-ended) — ideal when you can't uniquely resolve someone. API: GET /person/identify.

Input parameters:

- `birth_date` (string): Birth date (yyyy or yyyy-mm-dd).
- `company` (string): Company name, website, or PDL company id the person works at.
- `country` (string): Country name, e.g. 'united states'.
- `email`: Email address, or an array of email addresses.
- `first_name` (string): First / given name.
- `last_name` (string): Last / family name.
- `lid` (string): LinkedIn numerical ID.
- `locality` (string): City / locality, e.g. 'san francisco'.
- `location` (string): Free-text location, e.g. 'San Francisco, CA, USA'.
- `name` (string): Full name, e.g. 'Sean Thorne'.
- `pdl_id` (string): PDL persistent ID for a person record.
- `phone` (string): Phone number (E.164 or local).
- `postal_code` (string): Postal / ZIP code (assumed US if no country).
- `pretty` (boolean): Pretty-print the JSON response.
- `profile`: Social profile URL(s), e.g. a LinkedIn URL. String or array.
- `region` (string): State / region, e.g. 'california'.
- `school` (string): School name or website the person attended.
- `titlecase` (boolean): Titlecase the returned data (default false = lowercase).

### `pdl_person_search` (~255 tokens)

Search people

Search the full PDL Person Dataset with an Elasticsearch query object OR a SQL string over the Person Schema (e.g. everyone with job_title_role='engineering' at a company). Returns matching profiles sorted by completeness; paginate with scroll_token. Each returned record costs 1 credit. API: POST /person/search.

Input parameters:

- `dataset` (string): Dataset(s) to search: resume, email, phone, mobile_phone, street_address, consumer_social, developer, all. Comma-separate; prefix '-' to exclude.
- `from` (integer): Legacy offset (0-9999). Prefer scroll_token.
- `pretty` (boolean): Pretty-print the JSON response.
- `query` (string): Elasticsearch query as a JSON string, e.g. {"query":{"term":{"job_company_name":"people data labs"}}} — pass the value of "query".
- `scroll_token` (string): Pagination token from a previous response.
- `size` (integer): Number of records to return (1-100). Default 1.
- `sql` (string): SQL query string, e.g. SELECT * FROM person WHERE job_company_name='people data labs'.
- `titlecase` (boolean): Titlecase the returned data.

### `pdl_company_enrich` (~236 tokens)

Enrich a company

Find the single best-matching company record. Requires a non-ambiguous input — name OR website OR ticker OR profile (website/ticker/profile resolve more reliably than name). Returns firmographics (industry, size, location, etc.) or a 404 'no match' body. API: GET /company/enrich.

Input parameters:

- `country` (string): Company country.
- `locality` (string): Company city / locality.
- `location` (string): Company location free-text.
- `name` (string): Company name, e.g. 'People Data Labs'.
- `pdl_id` (string): PDL id for a company record.
- `pretty` (boolean): Pretty-print the JSON response.
- `profile` (string): Company social profile URL, e.g. a LinkedIn company URL.
- `region` (string): Company state / region.
- `ticker` (string): Stock ticker for a public company, e.g. 'AAPL'.
- `titlecase` (boolean): Titlecase the returned data.
- `website` (string): Company website, e.g. 'google.com' (most reliable).

### `pdl_company_search` (~204 tokens)

Search companies

Search the full PDL Company Dataset with an Elasticsearch query object OR a SQL string over the Company Schema (e.g. all SaaS companies with 50-200 employees in the US). Paginate with scroll_token. Each returned record costs 1 credit. API: POST /company/search.

Input parameters:

- `from` (integer): Legacy offset (0-9999). Prefer scroll_token.
- `pretty` (boolean): Pretty-print the JSON response.
- `query` (string): Elasticsearch query as a JSON string, e.g. {"query":{"term":{"industry":"computer software"}}} — pass the value of "query".
- `scroll_token` (string): Pagination token from a previous response.
- `size` (integer): Number of records to return (1-100). Default 1.
- `sql` (string): SQL query string, e.g. SELECT * FROM company WHERE industry='computer software'.
- `titlecase` (boolean): Titlecase the returned data.

### `pdl_ip_enrich` (~132 tokens)

Enrich an IP address

Enrich an IP address with its location, company, and (optionally) associated person data via a 1:1 match against PDL's IP dataset. API: GET /ip/enrich.

Input parameters:

- `ip` (string, required): The IP address to enrich, e.g. '72.212.42.169'.
- `min_confidence` (string): Minimum confidence level required to return a match.
- `pretty` (boolean): Pretty-print the JSON response.
- `return_person` (boolean): Include associated person data if available.
- `titlecase` (boolean): Titlecase the returned data.

### `pdl_autocomplete` (~144 tokens)

Autocomplete search values

Get suggested values for a search field along with the number of available records for each — useful for building valid Person/Company Search queries. Free on all plans. API: GET /autocomplete.

Input parameters:

- `field` (string, required): Field to autocomplete: e.g. company, school, location, region, country, industry, title, role, sub_role, skill, major.
- `pretty` (boolean): Pretty-print the JSON response.
- `size` (integer): Max suggestions to return. Default 10.
- `text` (string): Partial text to get suggestions for, e.g. 'stanf'.
- `titlecase` (boolean): Titlecase the returned data.

### `pdl_job_posting_search` (~170 tokens)

Search job postings

Search PDL's Job Posting Dataset (millions of active & historical postings sourced from company career pages) with an Elasticsearch query object OR a SQL string. Beta — may require plan access (HTTP 403 if not enabled). Each returned posting costs 1 credit. API: POST /job_posting/search.

Input parameters:

- `pretty` (boolean): Pretty-print the JSON response.
- `query` (string): Elasticsearch query as a JSON string, e.g. {"query":{"term":{"title_role":"engineering"}}} — pass the value of "query".
- `scroll_token` (string): Pagination token from a previous response.
- `size` (integer): Number of records to return (1-100). Default 1.
- `sql` (string): SQL query string over the job posting dataset.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/io-usefulapi-peopledatalabs/peopledatalabs#diagnostics

## Score history

- 2026-08-03: 70
- 2026-08-02: 28
- 2026-08-01: 18
- 2026-07-31: 69
- 2026-07-30: 66
- 2026-07-29: 67
- 2026-07-28: 67
- 2026-07-27: 66
- 2026-07-26: 12

## Links

- Remote endpoint: https://peopledatalabs.usefulapi.io/mcp
- Repository: https://github.com/m190/usefulapi-mcp
- Changelog RSS feed: https://verifymcp.io/servers/io-usefulapi-peopledatalabs/peopledatalabs/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-usefulapi-peopledatalabs/peopledatalabs/changelog.json
- HTML version of this page: https://verifymcp.io/servers/io-usefulapi-peopledatalabs/peopledatalabs