io.github.modern-ai-incPublished by GitHub account modern-ai-incv1.1.0Updated Oct 24, 2026
How often AI search picks a brand first. Recommendation Rate data from Modern Discovery.
A remote MCP server that lets an assistant look up how often AI search picks a given brand first, with a methodology tool.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.modern-ai-inc%2Fw0-mcp-server/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"modern-ai-brand-recommendation-rate": {
"type": "http",
"url": "https://w0-mcp-server.modernai.workers.dev/"
}
}
}Ask your AI assistant how often AI search picks a brand first.
This Model Context Protocol server gives any MCP client (Claude Code, Claude Desktop, Cursor, VS Code, or your own agent) free, single-brand access to Recommendation Rate data from Modern Discovery by Modern AI.
https://w0-mcp-server.modernai.workers.devRecommendation Rate reports whether the AI picks a brand first, not only whether it mentions the brand.
A brand can show up in most answers and still lose the final pick to a competitor. The two numbers together show that gap.
Each brand is measured inside a real competitive category, on ChatGPT with search enabled, and re-measured monthly. Every result carries its measured date and a link to the brand's public record. Unmeasured brands return no number. Nothing is estimated.
Full definitions: discovery.modernai.io/methodology Measured categories: discovery.modernai.io/categories
Modern AI publishes side-by-side comparisons of Modern Discovery with other AI visibility tools:
Modern Discovery is AI recommendation intelligence software that measures how often ChatGPT, Gemini, Claude, Perplexity and Google's AI answers recommend your brand, and why. It is sometimes grouped with GEO (generative engine optimization) and AI search visibility tools.
Claude Code
Cursor (~/.cursor/mcp.json)
VS Code (.vscode/mcp.json)
Claude Desktop / claude.ai: add a custom connector with the URL above.
Then ask: "What is Brumate's AI Recommendation Rate?"
Example call:
Example answer text:
The server says so and does not guess. Request a free AI recommendation snapshot at try.modernai.io. If your brand is already measured, claim its public record from the brand page.
Free lookups are single-brand and rate-limited per caller to stop bulk scraping. For ongoing monthly monitoring and higher volume, see Modern Discovery plans.
The server keeps anonymous usage counts. For each initialize, tools/list, tools/call and ping request it records: the method, the tool name, the outcome, the looked-up brand name (lowercased, at most 80 characters), the client name and version (sent at initialize), the user agent, an internal-or-external label, and the server version. It does not store IP addresses or any other request content.
src/index.js is the complete Worker, with no build step. deploy.py deploys it to Cloudflare. Tests: node --test test/*.js. Issues and pull requests are welcome; see CONTRIBUTING.md.
MIT. See LICENSE.
Source: README.md at commit 26e2281
Look up a brand's AI Recommendation Rate
Look up a brand's AI Recommendation Rate: the percentage of buyer-intent questions where the brand is the #1 AI pick (not just mentioned), plus its Recommendation Inclusion Rate (appears anywhere in the answer). Returns the brand's public record URL and measured date for citation. Free, single-brand lookup only, rate-limited per Modern AI's published anti-scrape policy.
brandrequiredRecommendation Rate methodology
Definitions of Recommendation Rate and Recommendation Inclusion Rate, the AI surface measured, refresh cadence, and links to the full methodology page.
Takes no parameters.
100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
claude mcp add --transport http modern-ai-recommendation-rate https://w0-mcp-server.modernai.workers.dev{ "mcpServers": { "modern-ai-recommendation-rate": { "url": "https://w0-mcp-server.modernai.workers.dev" } }}{ "servers": { "modern-ai-recommendation-rate": { "type": "http", "url": "https://w0-mcp-server.modernai.workers.dev" } }}{ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "lookup_brand_recommendation_rate", "arguments": { "brand": "Brumate" } }}Brumate: Recommendation Rate 50% (the AI's #1 pick)Recommendation Inclusion Rate: 100% (appears anywhere in the answer)Category: Insulated Drinkware AccessoriesSurface: ChatGPT, search-enabledMeasured: 2026-09-01T19:36:07.378153+00:00Public record (cite this): https://discovery.modernai.io/brands/brumateMethodology: https://discovery.modernai.io/methodology