Panda Leads Tools

Why it got a B

An MIT community server from one developer (GitHub pandadad0214, "Panda Federation"), on PyPI and in the official MCP Registry since November 2026. It's a thin wrapper: each tool runs one of the author's Actors on Apify, billed to your own Apify account. Fifteen tools build lead lists: local businesses from OpenStreetMap, US healthcare providers, podcasts, company hiring, company websites and team pages, trucking carriers, nonprofits, building permits, new businesses in Florida, Texas, New York and Colorado, H-1B sponsors and French companies. Many rows are about people, not companies. npi_provider_lists returns individual providers' NPI numbers, names, specialties, practice addresses and phones. company_team_finder reads company team pages for names, titles, published emails, LinkedIn links and a guessed email (emailGuess, with a confidence level; verify it before you send). podcast_leads_finder returns hosts' emails from their RSS feeds, and the registry tools return company officers, CEOs, registered agents or directors (Colorado flags agents who are likely the owner). company_hiring_signals stays at company level: open-job counts and job titles, no people. The data is public, but emailing or calling these people is covered by privacy and anti-spam laws such as GDPR and CAN-SPAM, so check yours before you use a list. Results cost about $0.001 to $0.004 each. Each call is capped at $0.50 by default, but the AI can raise that cap to $25 for a call, and PANDA_MAX_CHARGE_USD only changes the default. Every tool is marked read-only, so a client that skips approval for read-only tools won't ask before a call spends money. The Actors that do the work are closed source, but they run with Apify's limited permissions, so they can't read the rest of your Apify account. No advisories on record. Biggest deduction: the README has you paste your default Apify token, which can use your whole Apify account; create a scoped token that can only run pandadad0214's Actors, with an expiry date, and use that instead.