How to Connect Lusha to Microsoft Copilot via MCP

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

Lusha + Microsoft Copilot

Give your AI Lusha B2B data: find contacts and companies by name, email, LinkedIn URL or domain, prospect by job title, seniority, industry, size and location, check your credits, and reveal emails, phone numbers and firmographics only for the records you pick. Also reads job change and company signals.

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:

LUSHA_API_KEY

Step 1 — Get credentials

1. Sign in to Lusha with an account that has API access. Only account admins and managers with API access see the API page.
2. Open API → Manage API Keys at https://dashboard.lusha.com/api/manage-api-keys and create or copy a key.
3. Paste it into LUSHA_API_KEY and install the connector. The key is sent as the api_key header and only to Lusha.
4. Check the setup with lusha_get_account_usage: it shows the credits left and the price of each action, and uses no credits.

Calls that return records cost credits, so the AI asks first: Lusha API v3 charges your account's credit pool for every call that returns data, searches included. Prices depend on your plan, and lusha_get_account_usage lists them per action (search, company reveal, email, phone and so on).

• Free: lusha_get_account_usage (at most 5 calls a minute), lusha_list_filters, lusha_get_filter_values, lusha_list_signal_types, and polling an enrichment job with lusha_get_enrich_job.
• A small charge per result found (nothing when not found): lusha_search_contacts, lusha_search_companies, lusha_prospect_contacts and lusha_prospect_companies. They return previews without emails or phone numbers, plus what an enrichment would reveal and what it would cost.
• More credits: lusha_enrich_contacts (per revealed email and per revealed phone; a phone usually costs several times an email), lusha_enrich_companies (per company), and lusha_get_contact_signals and lusha_get_company_signals (per matched signal).

Before any call that costs credits the AI tells you what it will run, for how many records and what it can cost, and waits for your yes. It keeps result pages small and reveals only the fields you need: emails alone cost less than emails and phones.

How it works: for people and companies you already know, the AI searches by Lusha id, LinkedIn URL, email, name plus company, or company name and domain. For new prospects it first reads the valid filter values (seniority, departments, industries, company sizes, revenue, locations, technologies) and then prospects with include and exclude filters. After you pick records it enriches them by Lusha id, up to 100 at a time. When Lusha answers with a job for data that arrives later, the AI waits and reads the job for free.

Signals: job changes and promotions of contacts, and hiring surges, headcount changes, website traffic, IT spend, news and intent changes at companies. lusha_list_signal_types lists them for free; reading signals costs credits per match.

Personal data, B2B use only: contact records describe real people: names, job titles, employers, work and private email addresses, mobile and direct phone numbers. Use them only for a legitimate business purpose you can justify, such as B2B sales or recruiting under legitimate interest, in line with the GDPR, CAN-SPAM and Lusha's terms. Keep only what you need, respect the do-not-call flag on phone numbers and the EU contact flag, and do not build mass mailing lists or look up private individuals. Lusha itself withholds some people for legal reasons (HTTP 451 or COMPLIANCE_RESTRICTED). The connector gives the AI the same rules.

Rate limits: 25 requests a second per account by default, plus hourly and daily quotas by plan. A 429 means waiting and trying again.

Common errors: 401: the key is wrong, revoked or missing. 402: no credits left. 403: the account is inactive or the plan lacks a feature. 400: an invalid filter value or parameter, named in the answer. 451: Lusha cannot return this person for legal reasons. A successful answer can still mark single records as not found, restricted or failed.

The connector never changes data in Lusha. It does not search and enrich in one call (that would skip your confirmation), and it does not cover lookalikes, buying groups, scoring, website visitors, CRM export, webhooks or the legacy v2 endpoints.

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 Lusha 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

• "How many Lusha credits do we have left, and what does revealing an email or a phone number cost on our plan?"
• "Find heads of marketing at SaaS companies in Germany with 51 to 500 employees. Show me a small page of previews and tell me what the search costs first."
• "Reveal only the work emails of the first two contacts. Tell me the credit cost before you run it."
• "Check acme.com, northwind.com and contoso.com for hiring surges and headcount changes. Tell me the cost first."
• "Did any of these five contacts change jobs or get promoted recently?"

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