# People Data Labs MCP connector

The People Data Labs connector brings person profiles, company profiles, job postings and record clean-up to Claude, ChatGPT, Cursor, Microsoft Copilot and the Elaichi Agent, with every lookup made by a named person and written to an audit log.

Source: https://elaichi.ai/connectors/peopledatalabs/

## Facts

| | |
| --- | --- |
| Application | People Data Labs |
| Category | Sales Intelligence |
| AI tools | 17 |
| Authentication | Connects with an API key |
| Bring your own OAuth app | No |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once People Data Labs is connected

- Enrich jane@acme.com and tell me her current title and company
- Find VP of engineering profiles at fintech companies in Austin
- Search job postings for data engineers in Berlin posted this week

## Connect People Data Labs in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick People Data Labs.
2. Optionally set Share with, then press Connect.
3. Paste a People Data Labs API key. One person generates a token in People Data Labs and pastes it once. Everyone else works through Share with, and never sees it.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which People Data Labs tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## People Data Labs MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## People Data Labs MCP connector for Claude Code

Endpoint: https://api.elaichi.ai/mcp

1. In a terminal, run `claude mcp add` with the endpoint.
2. Start Claude Code and run `/mcp`.
3. Pick elaichi, then sign in and approve in the browser.

```bash
claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
```

Use `--scope project` instead to share it with the repository through `.mcp.json`.

## People Data Labs MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web. The plugin directory lives at chatgpt.com/plugins.

## People Data Labs MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## People Data Labs MCP connector for Microsoft Copilot

Endpoint: https://api.elaichi.ai/mcp

1. In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
2. Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
3. Create a new connection, sign in and approve, then press Add to agent.
4. Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.

Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.

## Connect People Data Labs to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Every scope the client asks for starts ticked except "Delete things", which you tick yourself. Calling a People Data Labs tool needs "Use your connected apps". Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Think hard before granting Use your connected apps, which can also delete in connected apps and cannot be undone.

## What teams do with People Data Labs through Elaichi

### Fill in a lead before the first call

Sales. Give the agent an email address or LinkedIn URL and get back the person's current title, company, location and work history. Walk into the call knowing who you are talking to.

### Build a target account list by industry

Marketing. Search People Data Labs companies by industry, headcount and country, then enrich each one with its website, founding year and size. The list is ready for a campaign in minutes rather than days.

### Find candidates by title, skill and location

Recruiting. Search for people with a given job title, skill set and city, and enrich the strongest matches before reaching out. Pull live job postings to see which competitors are hiring for the same roles.

### Clean up messy company and location fields

RevOps. Hand the agent a batch of free-text company names, locations and school names and get back standardized matches. Enrich hundreds of records in one bulk request instead of one at a time.

### Spot job changes across your contacts

Customer success. Search the People Data Labs changelog for contacts who have moved roles or companies since your last check. Reach out to the champion at their new employer before a competitor does.

### Answer a data subject request on time

Privacy. Download the People Data Labs subject request file when a person asks what is held about them. The agent fetches it, and the audit log shows exactly who requested it and when.

## Elaichi vs Zapier MCP vs Composio for People Data Labs

All three can connect People Data Labs to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over People Data Labs tools | Allow or restrict single People Data Labs tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per People Data Labs call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect People Data Labs to Claude?

First, in Elaichi, choose People Data Labs and paste your People Data Labs API key. There is no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Sign in with your Elaichi account and People Data Labs is ready to use.

### Does People Data Labs work with ChatGPT and Cursor as well as Claude?

Yes. Once People Data Labs is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any other MCP client and the Elaichi Agent. You connect People Data Labs once and every client picks it up.

### What can an AI agent actually do with People Data Labs?

It can look up a person from an email address, name or LinkedIn URL and return their title, employer and location, and it can enrich a company from its domain with headcount, industry and founding year. It can search People Data Labs for people by role and city, search job postings, check who in a list has changed jobs, and standardize messy company, school and location names. Short concrete asks work better than long sentences, so "enrich acme.com" beats a paragraph.

### Does connecting People Data Labs give the AI access to everything in my account?

No. The People Data Labs API key sets the outer limit, and every call is made by a named person signed into Elaichi, so it runs inside the role that person holds. Elaichi can narrow what a role or an individual is allowed to do with People Data Labs, and it never widens access beyond what the key already permits.

### Can my team share one People Data Labs connection?

Yes. One person enters the People Data Labs API key in Elaichi and shares the connection with a team, and nobody else ever handles or sees the key. Each teammate still signs into Elaichi as themselves, so every People Data Labs lookup in the audit log carries the name of the person who ran it.

### Can I stop an agent from running bulk enrichment or downloading subject requests in People Data Labs?

Yes. Restrictions in Elaichi work per action, so you can restrict bulk enrichment or subject request downloads in People Data Labs for a role or for one person while leaving single lookups open. A restricted action still appears in Elaichi's tool search, flagged as restricted, but no client can run it, whatever the prompt says.

### What happens to a People Data Labs connection when someone leaves?

Offboarding them in Elaichi ends their access to People Data Labs at once, in every client they used. A shared People Data Labs connection keeps working for everyone else on the team. If you want it gone entirely, disconnecting People Data Labs once in Elaichi removes it from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client.

### Does the People Data Labs MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. People Data Labs is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for People Data Labs?

Yes. Both let Claude, ChatGPT or Cursor use People Data Labs. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every People Data Labs call.

### How is Elaichi different from Composio for People Data Labs?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to People Data Labs: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 17 People Data Labs tools

Every tool below is callable through https://api.elaichi.ai/mcp once People Data Labs is connected, subject to the toolbox it is in and the restrictions on the caller.

- **People Data Labs people search** (Search). Search People Data Labs person records with an Elasticsearch query or SQL; 1 credit per returned record, 1-100 per page. Returns: status, data, total, scroll_token. Pass exactly one of query or sql. Paginate by passing the previous scroll_token; a null scroll_token means the last page; no-match queries return an empty result.
- **People Data Labs people enrich** (Action). Enrich a single person in People Data Labs. Returns: status, likelihood, data, matched. Required: profile, email, phone, email_hash, lid or pdl_id alone, or name (or first_name + last_name) plus a locator such as company, school, location or postal_code. No-match requests return 404 and are not charged.
- **People Data Labs people bulk enrich** (Action). Bulk enrich up to 100 people in one People Data Labs request; 1 credit per 200 results. Returns a JSON array of per-request objects: data, status, likelihood, and optional metadata. Requires requests (1-100 objects, each with params); set required, include_if_matched, titlecase, data_include, min_likelihood globally.
- **People Data Labs people identify** (Action). Identify a person in People Data Labs, returning up to 20 candidate profiles sorted by match score. Returns: status, matches (data, match_score, matched_on). Send at least one of profile, email, phone, email_hash, lid, street_address, locality, region, company, school, location, postal_code, name, or first_name + last_name. Each call consumes 1 credit, billed on 200 and 404; 404 when no match. Rate limit: 10 calls/min.
- **People Data Labs people preview enrich** (Action). Preview a Person Enrichment result in People Data Labs using the same inputs as the Person Enrichment API. Returns: status, likelihood, data. Enterprise purchase only; 404 means no match.
- **People Data Labs companies search** (Search). Search People Data Labs company records with an Elasticsearch query (query) or SQL (sql) filter. Returns: status, data, total, scroll_token. Page with scroll_token; size 1-100 (default 1); a 404 not_found (no records matched) is returned as an empty result {status:404, data:[], total:0}.
- **People Data Labs companies enrich** (Action). Enrich a single People Data Labs company with a one-to-one match. Returns the matched company record including status, id, name, and likelihood. Requires one of pdl_id, name, ticker, website, or profile. A 404 is returned when no match exists.
- **People Data Labs companies bulk enrich** (Action). Bulk enrich up to 100 People Data Labs companies in one request. Returns a JSON array of per-company results, each with data, status, and likelihood. Credits are deducted per 200-status result. Required: requests (an array of 1-100 objects, each with a params object).
- **People Data Labs companies clean** (Action). Clean a company in People Data Labs using its name, website or LinkedIn profile and return the cleaned company record. Returns: status, id, name, website, size, founded, industry, location, linkedin_url, linkedin_id, facebook_url, twitter_url, ticker, type, raw, score, fuzzy_match. Requires at least one of name, website or profile; a 404 means no match was found. Free; 10 requests/min and 10,000/month by default.
- **List all People Data Labs autocomplete suggestions** (List). Get People Data Labs autocomplete suggestions (name, count, meta) for one field, such as school or company. Required: field. Free; 60 requests/min and 1,000/day. The vendor's top-level fields array is not returned.
- **People Data Labs ips enrich** (Action). Enrich an IPv4/IPv6 address in People Data Labs with matching company data and optional person, location and metadata details. Returns: status, data. Required: ip. Consumes 1 credit per match; unmatched IPs return 404 unbilled; hosting, proxy, tor or relay IPs return 400. Rate limit: 100/min free, 1,000/min paid. IP metadata is a premium add-on (extra price).
- **People Data Labs job postings search** (Search). Search People Data Labs job postings (beta; access must be requested from PDL) using exactly one search mode: field filters (AND-combined) or an Elasticsearch v7.7 query. Consumes 1 credit per record returned; pages via scroll_token. Returns: status, data, total, scroll_token, dataset_version. Required: one field filter or query in the body.
- **People Data Labs job titles enrich** (Action). Clean a raw job title with People Data Labs. Returns: status, data (cleaned_job_title, similar_job_titles, relevant_skills); the reference page shows these three keys at the top level instead, so read both. Required: job_title. A 404 is returned when no matching job title is found; charged per match.
- **People Data Labs locations clean** (Action). Clean a free-form location string into a structured location record in People Data Labs. Returns: name, locality, region, subregion, country, continent, type, geo. Required: location. A 404 means the location could not be parsed. Free; 10 requests/min and 10,000/month by default.
- **People Data Labs person changelogs search** (Search). Track person record changes between two People Data Labs dataset versions. Returns: status, data. Required: origin_version and current_version (valid and consecutive). Supply type unless submitting ids instead; each records array holds up to 1000 entries; paginate with the returned scroll_token. Paging is complete when scroll_token is null or PDL answers 404 (returned here as {status:404, data:{}}).
- **People Data Labs schools clean** (Action). Clean a school name, website, or LinkedIn profile in People Data Labs and return the cleaned school record. Returns: name, type, id, location, linkedin_url, facebook_url, twitter_url, linkedin_id, website, domain. Requires at least one of name, website, or profile; a 404 means no match was found. Free; 10 requests/min and 10,000/month by default.
- **People Data Labs subject requests download** (Download). Download the list of person IDs that have opted out of People Data Labs data. Takes no input parameters. Returns a plain-text response (not JSON): a first line of pdl_id followed by one PDL ID per line for each opted-out person. Through MCP the list is not returned inline; download it through the Proxy API.
