Connect People Data Labs to Microsoft Copilot via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → People Data Labs, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

People Data Labs + Microsoft Copilot

Give your AI B2B people and company data from People Data Labs: enrich a person or company from an email, profile or website, identify people from loose details, search people and companies with SQL, find the company behind an IP address, and clean names, locations and job titles.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

PEOPLE_DATA_LABS_API_KEY

Step 1 — Get credentials

1. Sign up at https://dashboard.peopledatalabs.com. The Free plan needs no card.
2. Open API Keys in the dashboard and copy the key.
3. Paste it into PEOPLE_DATA_LABS_API_KEY and install the connector. The key is sent only to People Data Labs.
4. Start with a free tool such as people_data_labs_autocomplete or one of the cleaners: they use no credits.

Personal data and GDPR: person results describe real people: names, employers, work history, locations and, depending on your plan, emails and phone numbers. Use them only for a purpose you can justify, such as B2B sales or recruiting under legitimate interest, keep only what you need, and remember that people in the EU have the right to be informed and to object. Do not look up private individuals out of curiosity, and do not combine results to profile someone beyond your stated purpose. The connector gives the AI the same rules.

Billed to your own PDL credits: lookups spend the monthly credits of your People Data Labs account (Free plan: up to 100 a month; Pro from $98 a month with 350 credits and up), counted separately for each API:

• Person and company enrichment, IP enrichment and job title enrichment: 1 credit only when a match is found. No match (404) is free.
• Person identify: 1 credit per call, also when nothing is found, whatever the number of profiles returned.
• Person and company search: 1 credit per record returned. The connector asks for 1 record by default, and the AI checks the total before it fetches more.
• Company, location and school cleaners and autocomplete: free (cleaners up to 10,000 calls a month, autocomplete 1,000 a day on self-serve plans).

The AI asks you before a search with a large size or a long series of lookups.

What it does: enrich one person from an email, a phone number with country code, a LinkedIn URL, or a name plus company, school or location, and only pay for matches that have what you need (for example an email); identify up to 20 candidates from loose details; search people and companies with SQL (SELECT * FROM person WHERE ...) or an Elasticsearch query; enrich a company from its website, name, profile or ticker; find the company behind an IP address, such as a website visitor; and get similar titles and skills for a job title. Values in PDL are lower case, so the AI uses autocomplete and the cleaners to find the exact titles, companies and locations before a search.

Rate limits (defaults): enrichment 100 a minute on Free and 1,000 on paid plans (company enrichment 10 a minute on Free); identify, searches and cleaners 10 a minute.

Common errors: 404 means no match: not a faulty request and, except for identify, not charged. 401: the key is wrong, revoked or missing. 402: the credits of this API are used up for the month; upgrade or wait for the reset. 400: too few inputs (for example a name without company or location), a malformed SQL or Elasticsearch query, or an IP address that belongs to a hosting provider or proxy. 429: too many calls a minute; wait and try again.

The connector does not do bulk enrichment, the person changelog, job posting search, skill enrichment, the preview APIs or the sandbox.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Microsoft Copilot

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Microsoft Copilot uses MCP servers through agents built in Copilot Studio: you add AnythingMCP to an agent as a tool, then publish the agent to Microsoft 365 Copilot and Teams. Copilot Studio connects from Microsoft's cloud over Streamable HTTP, which AnythingMCP supports.

1. In Copilot Studio, open your agent (or create one), go to Tools and choose Add a tool → New tool → Model Context Protocol.
2. Enter a Server name (for example AnythingMCP), a Server description that says what the connector does, and the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID. Copilot Studio uses the description to decide when to call the server.
3. Under authentication, choose API key, set Type to Header and the header name to X-API-Key, then select Create.
4. In Add tool, choose Create a new connection, paste an MCP API key from AnythingMCP (MCP Servers → your server → API keys) and select Add to agent.
5. Try it in the agent's Test pane: ask for something that needs the People Data Labs tools.
6. Select Publish, then Channels → Microsoft 365 and Microsoft Teams, keep Make agent available in Microsoft Copilot selected and choose Add channel. See agent in Teams installs it for you; in Microsoft 365 Copilot, type @ and pick the agent.

Prefer per-user sign-in? Choose OAuth 2.0 → Dynamic discovery instead of an API key: each user then signs in to AnythingMCP the first time the agent calls it.

Self-hosting? Use your instance's public HTTPS address instead of https://cloud.anythingmcp.com. Copilot Studio connects from Microsoft's cloud, so localhost does not work.

Available tools

Example prompts

• "Look up the company behind northwind-logistics.com: industry, employee count, headquarters and founding year."
• "How many heads of procurement work at logistics companies in Germany with 51 to 200 employees? Tell me the total first, then show me 5."
• "Which company is behind the IP address 203.0.113.42 that visited our pricing page today?"
• "A lead booked a demo with [email protected]. What is her current job title and company?"

FAQ

Which Copilot is this for? Microsoft 365 Copilot at work, through agents built in Copilot Studio. The Microsoft Copilot app for personal accounts has no option to add your own MCP server.

What do I need? A work account with access to Copilot Studio (a license or a trial) to build the agent. People who use it in Microsoft 365 Copilot or Teams need access to the agent: share it with them, or ask an admin to publish it to the organization. If your organization applies data policies to Power Platform connectors, they cover MCP servers too.

The agent doesn't call the tools. Check that the header name is exactly X-API-Key and that the key belongs to the same MCP server as the URL, and make the server description specific: Copilot Studio uses it to decide when to call the server. Publish the agent again after each change; in an open chat, type "start over" to get the new version.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT
• Connect to Cursor
• Connect to Gemini
• Connect to Meta Muse