# SpendSight

> You saw the commercial. SpendSight scores prescription drugs on clinical evidence, then prints the manufacturer's ad budget right next to the score, so patients, clinicians, and researchers can tell whether a drug is better or just advertised more, before the ten minutes with the doctor start.

SpendSight compares medications by clinical quality rather than marketing muscle. Each drug gets a Quality Score from 0 to 100, a fixed weighted composite of clinical trial efficacy (40%), patient outcomes (25%), FDA approval status (20%), and safety profile (15%). Beside that score, SpendSight prints the manufacturer's direct-to-consumer advertising spend from MediaRadar tracking, a Value Ratio (quality points per million ad dollars), Spend Alerts when an advertising pattern breaks trend, and a Telehealth Connect comparison of legitimate telehealth prices for the same prescription. Every figure links to its source in FDA OpenFDA, ClinicalTrials.gov, MediaRadar, or SEC filings. Advertising spend never enters the Quality Score; it is reported beside it.

The working example is the GLP-1 class audit shown in the demo. Over nine months (Jan to Sep 2025), Wegovy spent $316M on consumer ads for a 72/100 Quality Score (Value Ratio 0.23), while Zepbound spent $131M for an 89/100 score (Value Ratio 0.68) and 47% greater average weight loss. Mounjaro leads the class on value at 1.02. The four audited drugs spent a combined $699M on ads in that period. SpendSight is not medical advice; it organizes public data so users can have better-informed conversations with their clinicians.

Pricing is simple. SpendSight costs patients $0, with no credit card, no trial clock, and no plan to change that. Revenue comes from disclosed referral commissions paid by telehealth partners when a user chooses to fill a prescription through one of them. The commission amount is printed on every listing, never influences a Quality Score, and no money is accepted from drug manufacturers. The product is pre-launch and the waitlist is open.

For AI agents, SpendSight exposes a Model Context Protocol (MCP) server over streamable-HTTP transport with no authentication (the tools are public). The server is mounted at /mcp, so the JSON-RPC endpoint lives one level deeper, at https://spendsight.health/mcp/mcp; point streamable-HTTP clients at that full path. Two tools are available via the standard tools/list call. `get_product_info` returns name, description, features, target audience, data sources, the Quality Score methodology, an example comparison, pricing, and launch status. `submit_interest` registers a user's interest in early access (email required; name, persona, and message optional); valid persona values are patient, caregiver, healthcare_provider, pharmacist, researcher, insurance, journalist, and other.

## Docs

- [Homepage](https://spendsight.health/): the SpendSight landing page with the Marketing Facts label, product monograph, methodology, and waitlist form
- [Live demo](https://spendsight.health/demo): the GLP-1 class audit with spend vs quality charts, the Head-to-Head value ledger, a live Spend Alert, and Telehealth Connect pricing

## For AI agents

- [MCP endpoint](https://spendsight.health/mcp/mcp): streamable-HTTP JSON-RPC endpoint for get_product_info and submit_interest (the server is mounted at /mcp)
- [MCP discovery](https://spendsight.health/.well-known/mcp.json): machine-readable advertisement of the MCP server and its tools
- [OpenAPI spec](https://spendsight.health/openapi.json): REST description of the site's HTTP endpoints for non-MCP agents
- [security.txt](https://spendsight.health/.well-known/security.txt): security contact for the site

## Optional

- [Sitemap](https://spendsight.health/sitemap.xml): crawlable URL list for the site
- [Contact](mailto:hello@spendsight.health): reach the SpendSight team directly