How to generate B2B leads with Claude

Prospecting has always been a tab-juggling job: LinkedIn in one window, a contact database in another, an email finder in a third, a spreadsheet holding it all together. AI assistants change the shape of that work. With MCP (Model Context Protocol), Claude and ChatGPT can call lead-data sources directly — which means you describe your ICP once and the assistant does the finding, enriching, and verifying for you.

This guide walks through the full workflow with Scout Mesh, an MCP gateway that connects your assistant to nine prospecting data sources through one endpoint.

What you need

• Claude (Pro, Team, or Enterprise) or ChatGPT with connector support
• A Scout Mesh account — new accounts start with $5 in free credits, which is enough to build a real lead list end to end

You do not need subscriptions to Lusha, People Data Labs, or any other database. The gateway carries the access; you pay each provider's unit price only for the calls you make.

Step 1 — Connect the gateway

Add the Scout Mesh MCP server to your assistant as a custom connector and sign in. From that point, every source in the mesh — People Data Labs, Lusha, ContactOut, GitHub, Hugging Face, prog.ai, TheirStack, Bouncer, and Exa — appears as tools the assistant can call. This is the only integration step.

Step 2 — Describe your ICP, not the query

Instead of fighting filter panels, tell the assistant who you actually sell to: "Heads of operations at 50-500 person logistics companies in the DACH region — we sell route-planning software, and get verified emails for the twenty best fits." The assistant picks the right source for each part of the job — company signals to find the accounts, contact databases for the people, the open web for context.

Step 3 — Search wide, spend narrow

A good assistant-driven search starts with the free and cheap layers: GitHub and Hugging Face searches cost nothing, Exa web research costs $0.007 per query, and TheirStack job-posting signals start at $0.04 a record. That is enough to map which companies fit your ICP — who runs the technology you integrate with, who is hiring into the team you sell to — before you spend a cent on contacts. The assistant builds the account list there, then spends on enrichment — a verified email or direct dial — only for the prospects that survive your review. You see each cost before it is incurred.

Step 4 — Verify before outreach

Every address that makes the list should pass through independent verification before it reaches your sequences. Bouncer checks deliverability at $0.008 per email — batch-verifying a 50-prospect list costs $0.40 and protects your sending domain from bounce damage. We wrote up why this matters in the email verification guide.

Step 5 — Hand off to your CRM

The output is a clean lead list — names, titles, companies, fit reasoning, verified contacts — assembled in one conversation, with duplicates across sources already merged. Export it to your CRM or outreach tool of choice; the prospecting part is done.

Why one gateway beats separate tools

Each database is strong somewhere: People Data Labs for profile depth, Lusha for direct dials, ContactOut for LinkedIn-to-email, TheirStack for buying signals. Wiring them into your assistant one by one means separate subscriptions, separate auth, and no way to compare sources. A gateway makes them one bill and one conversation — and lets the assistant cross-check one source against another, which is where the quality gains actually come from.