Loading...
EnsemblAI · docs
Point Claude Code, Claude Desktop, Codex, Cursor, or any MCP client at EnsemblAI and ask real questions about the PyPI and npm ecosystems — downloads, growth, dependencies, ownership. Setup is one command.
API and MCP access are part of the Pro plan (20K REST calls/mo · 5K MCP calls/day). Create an account, subscribe, and mint a key at /settings/api-keys.
Point any MCP client at the trial endpoint and start asking. No sign-up, no key: 10 calls per day, five read tools (search, package details, top downloads, compare, 6-month monthly charts).
claude mcp add --transport http ensemblai-trial https://mcp.ensemblai.com/try
With an API key (works headless — CI, scripts, remote agents):
claude mcp add --transport http ensemblai https://mcp.ensemblai.com/mcp \ --header "Authorization: Bearer ek_live_YOUR_KEY"
Or with OAuth (interactive; opens a one-click consent page):
claude mcp add --transport http ensemblai https://mcp.ensemblai.com/mcp
Settings → Connectors → Add custom connector, with URL https://mcp.ensemblai.com/mcp. Sign-in uses your EnsemblAI account (OAuth, one click).
# ~/.codex/config.toml
[mcp_servers.ensemblai]
url = "https://mcp.ensemblai.com/mcp"
http_headers = { "Authorization" = "Bearer ek_live_YOUR_KEY" }{
"mcpServers": {
"ensemblai": {
"url": "https://mcp.ensemblai.com/mcp",
"headers": { "Authorization": "Bearer ek_live_YOUR_KEY" }
}
}
}curl -s https://api.ensemblai.com/v1/packages/numpy \ -H "Authorization: Bearer ek_live_YOUR_KEY"
Full surface: OpenAPI schema · /llms-full.txt (generated from the live schema) · /llms.txt.
Raw registry download endpoints answer one package at a time over a capped recent window — no rankings, no growth math, no cross-ecosystem view, no ownership or dependency context. And the public datasets that do carry history mean running (and paying for) your own warehouse queries over terabyte-scale tables, then building the analytics layer yourself.
EnsemblAI pre-computes all of it and answers in milliseconds: multi-year download history in one call, ranked leaderboards, month-over-month growth and share-of-ecosystem, category-level aggregates — totals, growth, and leaders for an entire segment like AI/ML or DevOps at once, powered by a proprietary taxonomy classifying millions of packages by industry domain and technology category — plus ecosystem structure maps, corporate-ownership attribution, dependency risk, and normalized license/quality metadata. Identical fields for PyPI and npm.
Data & rankings
search_packages · get_package_details · get_package_metrics · get_package_health · top_downloads · growth_movers · time_series_for_packages · compare_packages · reference_values
Ownership & organizations
list_companies · list_company_packages · get_company_stats · list_organizations · get_organization_packages
Discovery & structure
get_package_dependencies · package_depgraph · package_cohort · ecosystem_map · ecosystem_clusters · audit_dependencies
Tracking (writes to your account)
list_watchlist · add_to_watchlist · remove_from_watchlist · list_alerts · create_alert · delete_alert · list_ensembles · get_ensemble · create_ensemble · update_ensemble · delete_ensemble · ensemble_analytics
Every call is scoped to your account: tier limits, rate limits, and row-level security apply identically to MCP, REST, and the dashboard.