Skip to content
Back to search

openlandscape

MarketplaceWorks with Claude CodeGitHub

Drug pipeline landscapes from public sources, for people and AI apps

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/theopenlabs--openlandscape/badge.svg)](/listings/theopenlabs--openlandscape)

HTML

<a href="/listings/theopenlabs--openlandscape"><img src="/api/listings/theopenlabs--openlandscape/badge.svg" alt="findsafeskills safety rating" /></a>

Install

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 11 lines
  1. {
  2. "name": "openlandscape",
  3. "owner": { "name": "OpenLandscape", "url": "https://openlandscape.app" },
  4. "plugins": [
  5. {
  6. "name": "openlandscape",
  7. "source": "./client",
  8. "description": "Drug pipelines, clinical trials and upcoming milestones from ClinicalTrials.gov, openFDA and SEC filings, every fact with its source. MCP connector plus a skill for landscape memos."
  9. }
  10. ]
  11. }
README.md · README · 236 lines
  1. <p align="center">
  2. <img src="brand/readme/banner.png" alt="OpenLandscape: every drug in development, with a source for every fact. Free to start, $49 a month, open source.">
  3. </p>
  4. <p align="center">
  5. Drug-pipeline landscapes from public registries: every drug for a disease, target or company,<br>
  6. who owns it, how far it has got and what happens next. On the web, and inside your AI assistant.
  7. </p>
  8. <p align="center">
  9. <a href="https://openlandscape.app"><b>openlandscape.app</b></a> ·
  10. <a href="https://openlandscape.app/landscapes/obesity">Try it (no account)</a> ·
  11. <a href="#use-it-from-your-ai-assistant">Use it from your AI</a> ·
  12. <a href="#openlandscape-and-the-big-pipeline-databases">vs Citeline</a> ·
  13. <a href="#what-it-costs">What it costs</a> ·
  14. <a href="#run-it-yourself">Run it yourself</a>
  15. </p>
  16. ## Why OpenLandscape
  17. **A source for every fact.** Every stage, date and number links to where it came from: ClinicalTrials.gov, the EU
  18. trials register, FDA, EMA, SEC filings or the company's own news. Nothing to take on trust.
  19. **A fair price.** Pipeline databases such as Citeline are sold to big pharma for tens of thousands a year, after a
  20. sales call. OpenLandscape starts free and costs $49 a month for everything.
  21. **Open by default.** The code is here, so anyone can see how every list is made. Your AI assistant can use it
  22. directly through the MCP connector.
  23. ## What it does
  24. ### A landscape for any disease, target or company
  25. Search for an area and get every drug in active trials: how it works, who owns it, its stage and its next date.
  26. Filter by stage, mechanism or China-based companies, copy the table or download it. Ready-made landscapes
  27. (obesity, PD-1/VEGF bispecifics, in vivo CAR-T, lung cancer) are free to read without an account.
  28. ![The obesity landscape: what changed this week, what is coming up, and every drug with how it works, company, stage and next date](brand/readme/landscape.png)
  29. ### Every drug, with its trials and sources
  30. A drug page says what the drug is in plain words, its other names and code names, every trial and what it is tested
  31. for, with the registry entry behind each line.
  32. ![The mazdutide page: stage, next date, active trials and targets, and what the drug is, in plain words with sources](brand/readme/drug.png)
  33. ### Every company's pipeline
  34. A company page lists everything it runs in trials, what is furthest along, what reads out next, and its SEC filings.
  35. ![The Novo Nordisk page: drugs furthest along, next date, number of drugs and trials, and the drug list](brand/readme/company.png)
  36. ### Ask your AI
  37. Add the connector to Claude, ChatGPT, Cursor or any MCP app and ask in plain words. The answer comes from the same
  38. data, with the sources attached.
  39. ![A real answer through the connector: oral GLP-1 pills in Phase 3 or later, with company, stage and next date](brand/readme/ai-answer.png)
  40. ### Follow an area, hear what changed
  41. Follow a landscape and see every new trial, moved date, approval and filing as it happens. A Monday email sums up
  42. the week and the dates coming up.
  43. <p align="center"><img src="brand/readme/monday-email.png" width="520" alt="The Monday email: what changed this week and what is coming up, each line with its source"></p>
  44. ### Light, dark and on your phone
  45. ![The PD-1/VEGF bispecifics landscape in dark mode](brand/readme/dark-mode.png)
  46. ![OpenLandscape on two phones: the obesity landscape and the mazdutide page](brand/readme/phones.png)
  47. <p align="center">
  48. <sub>Screenshots are from the live data. The account in them (alex@example.com) is made up.</sub>
  49. </p>
  50. ## OpenLandscape and the big pipeline databases
  51. | | OpenLandscape | Citeline and similar |
  52. |---|---|---|
  53. | Price | Free to start, then $49 a month | Tens of thousands a year |
  54. | Getting started | Sign in with your email, no card | A sales call and a contract |
  55. | Where the facts come from | Public registries, regulators, filings and company news, each linked | Also their own analysts and private research |
  56. | Code | Open source (AGPL-3.0) | Closed |
  57. The big databases cover more, because they pay analysts to read what is not public. OpenLandscape covers what is
  58. public, shows you the source for each line, and costs a small part of the price.
  59. ## What it costs
  60. - **Free:** no card, no time limit. The top 10 of any list, one landscape in full and 25 AI questions a month.
  61. - **Solo:** $49 a month or $490 a year (before VAT), for one person. Every list in full, follows, every change as it
  62. happens and the Monday email.
  63. Details: [openlandscape.app/pricing](https://openlandscape.app/pricing).
  64. ## Use it from your AI assistant
  65. OpenLandscape is a remote MCP server (Streamable HTTP). Server URL:
  66. ```
  67. https://openlandscape.app/mcp
  68. ```
  69. You sign in with your OpenLandscape account (OAuth) the first time; a free account works.
  70. - **Claude** (app or claude.ai): find OpenLandscape in the connector directory, or **Settings → Connectors → Add
  71. custom connector**, name it OpenLandscape and paste the URL.
  72. - **Claude Code:**
  73. ```bash
  74. claude mcp add --transport http openlandscape https://openlandscape.app/mcp
  75. ```
  76. - **Cursor:** add to `~/.cursor/mcp.json`:
  77. ```json
  78. { "mcpServers": { "openlandscape": { "url": "https://openlandscape.app/mcp" } } }
  79. ```
  80. - **Gemini CLI:** add to `~/.gemini/settings.json`, restart, and type `/mcp` to check:
  81. ```json
  82. { "mcpServers": { "openlandscape": { "httpUrl": "https://openlandscape.app/mcp" } } }
  83. ```
  84. - **ChatGPT** and other apps: step-by-step on [openlandscape.app/connect](https://openlandscape.app/connect).
  85. Then ask, for example: *"Map every amylin drug in Phase 2 or later, with next milestones."*
  86. Tools: `search`, `landscape`, `trials`, `catalysts`, `who_runs_trials`, `drug`, `changes`, `whoami`, and `show`
  87. (draws the answer as a card in apps that support it). Every answer carries its sources.
  88. More for AI tools: [openlandscape.app/ai](https://openlandscape.app/ai) and [openlandscape.app/llms.txt](https://openlandscape.app/llms.txt).
  89. ## Run it yourself
  90. ### What is in this copy, and what is not
  91. This repository is the open-source copy of the code. It has everything the site runs on: the data loaders, the
  92. grouping of trials into drugs, the website, sign-in, billing, the AI connector and the checks.
  93. It does not have the checked data. People check the rows by hand: which trial belongs to which drug, which company
  94. owns what, which names mean the same drug. That work is what OpenLandscape sells, so it stays private. Also private:
  95. company logos and the list of company aliases (for example that "GSK" means GlaxoSmithKline).
  96. So a copy you build yourself is thinner than the live site:
  97. - One checked area: obesity (`seed/obesity.js`), as a sample of what the checked data looks like.
  98. - Every other area is grouped automatically from the registry names. It works, but expect more duplicates and
  99. more drugs without a known company or target.
  100. - No company logos. Some company searches by short name find nothing.
  101. - The files that hold checked data are empty stand-ins with the right shape (in `seed/`), so the code runs.
  102. ### Run it on your computer
  103. Needs Node 22 or later, and about 1 GB of free disk space.
  104. ```bash
  105. npm install
  106. npm run ingest # downloads trials from ClinicalTrials.gov and approvals from openFDA, builds the database (15 to 20 minutes)
  107. npm start # http://localhost:8080
  108. ```
  109. Then open [localhost:8080/landscapes/obesity](http://localhost:8080/landscapes/obesity).
  110. The database is one SQLite file, `data/openpipeline.db` (a few hundred MB). `npm run ingest` builds it from public
  111. sources only. Most of the time goes on looking up drug names in public drug lists (the FDA substance registry and
  112. the NCI drug dictionary) and FDA labels. The drug-list lookups stop after a few minutes, so some names are not
  113. asked, and a few rows that are the same drug stay apart. Run `npm run ingest` again to refresh.
  114. No keys are needed to run it locally:
  115. - Without an email service, sign-in links are printed in the server log and shown on the page.
  116. - Without a Stripe key, the pricing page shows, but checkout says payments are not configured.
  117. To add keys, copy `.env.example` to `.env` and fill in what you need. [SETUP.md](SETUP.md) lists every account and
  118. key, and how to run your own server.
  119. #### Run the checks
  120. ```bash
  121. TODAY=2026-11-06 npm run check
  122. ```
  123. `TODAY` fixes the date, so date-based checks give the same answer on any day. Some checks need the private checked
  124. data. In this copy they print `SKIP` and do not fail. That is expected.
  125. ## How it works
  126. | Piece | What it does | Where |
  127. |---|---|---|
  128. | Trial loader | Downloads industry drug trials (phase 1 to 4) from the ClinicalTrials.gov API | `src/ingest/ctgov.js` |
  129. | Approval loader | Downloads the FDA's list of approved drugs (openFDA) | `src/ingest/openfda.js` |
  130. | Checked data | Hand-checked companies, drug names, approvals and filings, with sources | `seed/` (obesity only here) |
  131. | Grouping | Groups trials into drugs, merges names for the same drug (mazdutide = LY3305677 = IBI362), skips placebo and comparator arms | `src/ingest/link.js` |
  132. | Questions | Search, landscape, trials, catalysts, who runs trials, one drug, recent changes | `src/query.js` |
  133. | AI connector | The same questions for AI apps, as a remote MCP server | `src/mcp.js` |
  134. | Website | Landscape pages, dashboard, pricing, Stripe checkout, email sign-in | `src/server.js`, `src/pages/`, `web/` |
  135. | Client | The connector setup for Claude and ChatGPT, and skills for writing landscape memos | `client/` |
  136. Checked areas are listed in `seed/index.js`. To check a new area, add a seed file in the same format as
  137. `seed/obesity.js` and list it there.
  138. **Why the ClinicalTrials.gov API and not AACT?** AACT is a nightly database copy of the same registry. It needs an
  139. account, and we only need the industry drug trials, a small part of it. The official API serves the same records
  140. with no account.
  141. ## The AI connector
  142. The connector is a remote MCP server at `/mcp`. AI apps sign in with OAuth (`src/oauth.js`); `/mcp/u/<api-key>`
  143. also works for apps that take a plain address. It has eight tools:
  144. `whoami`, `search`, `landscape`, `trials`, `catalysts`, `who_runs_trials`, `drug`, `changes`.
  145. A ninth tool, `show`, draws the answer as a card inside Claude or ChatGPT. Set `AI_CARDS=0` in `.env` to turn cards
  146. off; `show` then goes away and the tools answer in text only.
  147. ## Rules the product follows
  148. 1. Every phase, date and number links to its source.
  149. 2. Facts from press reports carry a "news" tag. Name merges and mechanisms not yet confirmed carry an orange dot.
  150. 3. Every page says when the data was pulled.
  151. 4. Features not built yet show the month they ship.
  152. ## Contributing and security
  153. - How to send changes: [CONTRIBUTING.md](CONTRIBUTING.md)
  154. - How to report a security problem: [SECURITY.md](SECURITY.md). Please do not open a public issue for it.
  155. ## Licence
  156. - The app (server, data loaders, AI connector, website): AGPL-3.0, see `LICENSE`.
  157. - The client (`client/`): MIT, see `client/LICENSE`.
  158. The data the app downloads comes from ClinicalTrials.gov, openFDA and SEC EDGAR, under their own terms.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.