LeadDirect MCP
LeadDirect MCP finds B2B prospects by searching the web and crawling company sites for published contact details.
find_leads: search for companies matching a query, optionally set region, target lead count, exclusions, and save new de-duplicated leads toleads.csv.scrape_company: crawl one company URL/domain for published emails, phones, and social links.decode_cloudflare_email: decode Cloudflare email-protection strings.list_leads: show the latest rows fromleads.csv.
Decodes Cloudflare email-protection values, including data-cfemail attributes and /cdn-cgi/l/email-protection links, to recover published email addresses during lead extraction.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@LeadDirect MCP Find 10 lowbed semi-trailer dealers in France and save them to CSV"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
LeadDirect MCP
Live demo: https://lead-direct-mcp.vercel.app (mock mode, runs fully in the browser) · deploys automatically on every push to main
An MCP server for B2B prospecting from Claude Desktop, Cursor or any MCP client. Describe the companies you want ("lowbed semi-trailer dealers in France, skip the big brands") and LeadDirect searches the web, reads each company's own homepage, contact, about and imprint pages, and returns the contact details the company publishes: emails (including ones hidden by Cloudflare email protection), phone numbers, and LinkedIn / Facebook / Instagram / WhatsApp / X links. New leads go into a CSV, de-duplicated by domain.
MCP server | Python 3.10+ · FastMCP · httpx · BeautifulSoup · phonenumbers · ddgs |
Web demo | React 18 · TypeScript · Tailwind CSS · Vite, deployed on Vercel |
LeadDirect only collects what a company publishes on its own website. It does not guess personal addresses or probe mail servers.
Tools
Tool | What it does |
| Web search → one result per company domain (directories, marketplaces and social networks skipped, plus your |
| The same crawl for one URL or domain. |
| Decodes a |
| Shows the latest rows of |
Each lead lists emails with named contacts first and shared inboxes (info@, sales@, satis@,
kontakt@, …) after. Asset names (logo@2x.png), placeholders (you@example.com,
firstname.lastname@) and no-reply addresses are filtered out. Phone numbers are parsed with Google's
libphonenumber and printed in international format; pass region (e.g. FR) so national numbers parse.
Related MCP server: @bingeljell/lead-gen-mcp
Install
git clone https://github.com/weblinkify/lead-direct-mcp
cd lead-direct-mcp
python -m venv .venv && source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -e .MCP client config (claude_desktop_config.json, Cursor mcp.json, …):
{
"mcpServers": {
"leaddirect": {
"command": "/ABSOLUTE/PATH/lead-direct-mcp/.venv/bin/leaddirect",
"env": { "LEADDIRECT_OUTPUT_DIR": "~/Desktop" }
}
}
}leads.csv is written to LEADDIRECT_OUTPUT_DIR, else your Desktop, else ~/LeadDirect.
Prompting tips
Target and geography: the niche plus the country or region.
Local-language keywords:
semi-remorque surbaissée concessionnairefor France,ambalaj karton üreticifor Türkiye,Landtechnik Händlerfor Germany.Exclusions: pass large brands and portals in
exclude_domains.Qualification: ask the assistant to keep only companies that sell the product directly.
Find 10 dealers of lowbed semi-trailers in France. Search in French
("semi-remorque surbaissée concessionnaire"), region FR, and skip
schmitz-cargobull.com and krone-trailer.com. Put the results in a table with
named contacts first and their LinkedIn pages.Web demo
cd frontend
npm install
npm run dev # http://localhost:5173The companies are fictional (.example domains), but the HTML extractor and the Cloudflare decoder in
the demo are TypeScript ports of the server code and run for real. Paste any page's HTML to try them.
Vercel: import the repo and set Root Directory to frontend; frontend/vercel.json does the rest.
Development
make install # dependencies and git hooks
make check # lint, types, tests and build: everything CI runs before merge
make audit # pip-audit and npm auditResponsible use
Respect each website's terms and robots rules, and the email marketing law where you operate (GDPR / ePrivacy in the EU, CAN-SPAM in the US, KVKK in Türkiye). Published business contact details are not a licence to send bulk unsolicited email.
License
MIT
Available Tools
4 toolsdecode_cloudflare_emailDecode Cloudflare EmailA
Decode a Cloudflare email-protection string (the data-cfemail value or the part after '#').
Inputs: encoded (required). Returns: result
find_leadsFind LeadsC
Find companies for a query and collect their published contact details.
Inputs: query (required), save, region, target_leads, +1 more. Returns: result
list_leadsList LeadsB
Show the most recent rows of leads.csv.
Inputs: limit. Returns: result
scrape_companyScrape CompanyB
Crawl one company website (homepage + contact/about/imprint pages) for published contacts.
Inputs: url_or_domain (required), region. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a mostly distinct role: find_leads is a query-level search, scrape_company targets a single known site, decode_cloudflare_email is a narrow utility, and list_leads reads cached results. The main risk is overlap between find_leads and scrape_company, since both 'collect published contact details', but the descriptions make the bulk-vs-single distinction clear enough.
All four tools follow a consistent snake_case verb_noun pattern (find_leads, scrape_company, decode_cloudflare_email, list_leads). No mixing of conventions or vague verbs.
Four tools cover the core lead-generation pipeline (search, scrape, decode, list) without redundancy. It is on the lean side — a couple more operations would round it out — but nothing feels extraneous.
The create/scrape/read path exists, but there is no way to search or filter saved leads beyond 'most recent rows', no update/delete of entries, and no export or dedupe operation. These are workable gaps but real ones for a lead-management workflow.
Maintenance
Related MCP Connectors
Search people and companies, enrich profiles, and find email and phone over MCP.
Published emails, phones and social profiles for every website in a list, CSV or Google Sheet.
Local business & Google Maps B2B lead extractor MCP: phone, email, website, DNS & SaaS tech stack.
Emails, phones and social links from any list of websites. Pay only for sites with a contact.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables B2B research by finding verified work emails, extracting contacts, detecting tech stacks, and profiling DNS and SaaS, all through a suite of MCP tools.-
- AlicenseBqualityDmaintenanceEnables AI-assisted B2B lead generation by discovering, extracting, scoring, and exporting company leads from any MCP-compatible agent.310 npmMIT

Getlead MCP serverofficial
AlicenseNot gradedqualityCmaintenanceEnables finding B2B leads with verified work emails, finding and verifying email addresses, and running cold email outreach from any MCP client.1MIT
FullEnrich MCPofficial
AlicenseNot gradedqualityCmaintenanceEnables AI agents to search B2B people and companies, enrich contacts with verified emails and mobile phone numbers via waterfall enrichment across 25+ providers, and export results as CSV or JSON. Supports prospecting, org mapping, candidate sourcing, and outreach workflows through OAuth-authenticated remote access from any MCP-compatible client.14MIT