Skip to content
Pharma Observatory a Scientist.com platform

Biopharma research intelligence for people and AI agents

The public record on every trial, drug and company, already cross-referenced

Pharma Observatory matches clinical trials, drugs, companies, investigators, sites, patents, funding and FDA enforcement across their public sources. Look up a trial, drug or company and see what the public record holds on it in one place, with the figures on its page linked to the registry entry, filing or publication behind them. Your AI agent can use it too, over MCP, with a free endpoint that needs no account.

Connect your AI agent

Individual plan, $249 per seat per month. Card required. Your first charge is when the trial ends. Or browse the free condition and biomarker pages.

The Patent Cliff page in Pharma Observatory: three headline figures above a stacked bar chart of total revenue rolling off patent by year and company
The Patent Cliff view: total revenue rolling off patent, by year and company. Each drug is sized by the revenue its company discloses, or by US Medicare spend where none is disclosed.

For AI agents

Use it from your AI agent

Pharma Observatory has an MCP server. Add the free endpoint to Claude Desktop, ChatGPT, Claude Code or Codex and your agent can search and read our public condition, biomarker and organization pages. No account, no token.

Try it without an account

Claude Desktop

Add it as a custom connector in Claude Desktop or on claude.ai.

  1. Open Customize, then Connectors.
  2. Click + Add, then Add custom connector.
  3. Name it Pharma Observatory, paste the URL below as the remote MCP server URL, and click Continue.
  4. Review the authentication settings Claude detected and click Continue again.
  5. Under Authentication choose No sign in, then click Add.
  6. In a chat, click + at the lower left, then Connectors, and switch Pharma Observatory on.
Connector URL
https://pharmaobservatory.com/mcp/public/v1

Requires: Custom connectors are available on the Free (limited to one), Pro, Max, Team and Enterprise plans. On Team and Enterprise an Owner adds the connector first, under Organization settings, then Connectors, and members connect to it under Customize, then Connectors.

ChatGPT

Add it as a custom MCP server on the ChatGPT web app.

  1. On the web, open chatgpt.com/plugins.
  2. Select the plus button, then Add custom MCP server.
  3. Enter the name Pharma Observatory and paste the URL below as the Server URL.
  4. Set Authentication to No authentication.
  5. Review the risk warning and select I understand and want to continue, then select Create as a plugin.
  6. Install the new plugin from your personal plugins. Switch the ChatGPT homepage tab from Chat to Work, start a new Work chat, type @ and pick Pharma Observatory.
Server URL
https://pharmaobservatory.com/mcp/public/v1

Requires: Use ChatGPT on the web. OpenAI's documentation does not list which plans include custom MCP servers, and says workspace permissions and security restrictions apply, so on a work account your admin may have to allow it.

Claude Code

Register it with one command in a terminal.

  1. Run the command below in a terminal where Claude Code is installed.
  2. It registers the anonymous endpoint as an MCP server named pharma-observatory, with no sign-up and no token.
Terminal
claude mcp add --transport http pharma-observatory https://pharmaobservatory.com/mcp/public/v1

Requires: Claude Code installed.

Codex

Add a Streamable HTTP server to the Codex CLI configuration.

  1. Open ~/.codex/config.toml, or .codex/config.toml in a trusted project.
  2. Add the block below. Do not set a bearer token or headers: the anonymous endpoint refuses any credential.
  3. Restart Codex, then run /mcp in the Codex terminal UI to see pharma-observatory listed.
config.toml
[mcp_servers.pharma-observatory]
url = "https://pharmaobservatory.com/mcp/public/v1"

Requires: The Codex CLI installed.

Cursor

Add it with one click, or add it to your Cursor mcp.json.

  1. Select Add to Cursor. Cursor opens and asks you to confirm the server named pharma-observatory.
  2. Or add the block below to ~/.cursor/mcp.json, or .cursor/mcp.json in a project.
mcp.json
{
  "mcpServers": {
    "pharma-observatory": {
      "url": "https://pharmaobservatory.com/mcp/public/v1"
    }
  }
}

Requires: Cursor installed.

VS Code

Add it with one click, or add it to your VS Code mcp.json.

  1. Select Add to VS Code. VS Code opens and asks you to confirm the server named pharma-observatory.
  2. Or add the block below to .vscode/mcp.json in a workspace.
mcp.json
{
  "servers": {
    "pharma-observatory": {
      "type": "http",
      "url": "https://pharmaobservatory.com/mcp/public/v1"
    }
  }
}

Requires: Visual Studio Code installed.

It returns the same trimmed data our public pages show a visitor. The full tool set and every row need a plan. Start a 14-day trial for the full tool set. MCP access is included in every paid plan.

What is in it today

Counts from the database behind the product, rounded down to two significant figures. A + means at least that many.

Clinical trials 600,000+
Investigators 380,000+
Research sites 1 million+
Organizations 350,000+
Publications 790,000+
Molecules 4,500+

The data is public. The joining is the work.

ClinicalTrials.gov, FDA, SEC filings, PubMed and NIH each publish part of the picture, and each uses its own name for the same drug, company or physician. Answering one question means exporting from several of them and reconciling the names in a spreadsheet. Pharma Observatory does that matching ahead of time and shows you the result with the sources named.

One page per drug, company or person

A drug filed under a code name, a generic name and a brand name is one page here, with its trials, sponsors and patents attached. The same holds for a company and its subsidiaries, and for an investigator listed under several spellings.

Numbers you can trace to a source

On the page for a trial, drug, company or person, figures link to the registry entry, filing or publication behind them. When a reviewer asks where a number came from, you can follow it to the source. Summary views such as Patent Cliff combine those records.

The science and the business in one place

Trials, sites and investigators sit beside funding, ownership, patents and FDA enforcement. A question that crosses from the clinic to the company stays on one page.

Free to read

Judge the data on a subject you know

Open a disease or a gene you know well, without an account, and check what is on the page against what you already know.

How it works

From a name to the source record

  1. Search a name

    A drug, a company, a condition, an investigator or a site.

  2. Read one page

    What the public sources say about it, matched across the names each source used.

  3. Open the source

    On a trial, drug, company or person page, follow a figure to the registry entry, filing or publication behind it.

Inside the product

Four places to start

Each view draws on the same matched data, so a drug or a sponsor you find in one is the same page everywhere else.

Trials

Size up a field, then open a single study

Every study registered on ClinicalTrials.gov, grouped by phase, status, sponsor and indication. Start with how active an indication is and drill down to one protocol.

  • See how active an indication is and how its phase mix has shifted.
  • See who sponsors the work and what else they have run.
  • See which studies are starting, changing status or due to read out.

Conditions

Browse by disease, from therapeutic area to indication

Conditions follow the MeSH hierarchy. A search for a therapeutic area includes every indication beneath it, and you can step down level by level to see where the trials concentrate.

  • See which indications sit under a therapeutic area.
  • See which indications are crowded and which have few trials.

Drugs, companies and people

Every name, one page

Sapropterin and Kuvan are one drug here. An investigator listed under an NPI in one source and an ORCID in another is one person. Each page carries the full history under every name.

  • See what a compound is across every name it has been filed under.
  • Count the trials, patents and sponsors attached to it.
  • See the people and organizations behind the work.
  • See every name a source has used for it, gathered on one page.
  • Follow a figure on its page to the registry entry, filing or publication behind it.

Study Feasibility Planner

Turn a study concept into assumptions you can defend

Pick an indication and a design. The Planner benchmarks your enrollment rate against comparable completed trials, ranks candidate sites and estimates a budget range. Each step carries forward the numbers from the one before.

  • Get a realistic enrollment-rate range for the design.
  • See which sites fit the geography and the enrollment target.
  • Estimate the cost line by line.

Planner outputs are ranges drawn from comparable trials. They support an assumption and do not guarantee enrollment or cost. Planner access is set up per account and is not part of the Individual or Team plan.

The application

What you see after you sign in

Screenshots from the product, in light or dark to match your settings.

The trials list: a search box, a filter rail by condition and status, and a sortable table of studies
Filter every registered study by phase, status, sponsor or condition, and sort by any column.
The signed-in home: a search across every entity type, the latest trial events and links into each area
One search box for trials, drugs, conditions, companies, investigators and sites, beside the latest trial status changes.

Who it is for

Find your team's questions

One page per team, each listing what you can answer and where in the product you answer it.

Business development and licensing Open a company and see what it has approved, what is active, what it dropped, what it has raised and which patent and regulatory dates are coming. Figures link to the filing or registry entry they came from. Clinical operations and feasibility Benchmark enrollment, duration, site count and country mix against completed trials like yours, then see which studies are recruiting the same patients now. Commercial and lifecycle strategy Disclosed brand revenue, patent and exclusivity dates, and the FDA decisions ahead, together on one company page. Competitive intelligence and portfolio strategy Active programs by phase, discontinued programs, regulatory dates and the sponsors behind a disease or target, with each drug counted once under all its names. CRO business development See your trials the way a sponsor's outsourcing team sees them, then find the sponsors active in your strongest indications. Clinical outsourcing and CRO selection Filter CROs by indication, phase, region and start year, then open the trials behind each one before the RFP goes out. Investors and diligence Financing rounds and ownership from SEC filings, pipeline, patent exposure, upcoming decisions and FDA enforcement history for a company, each traceable to its filing. Medical affairs and KOL mapping Find the people who led trials in a disease, then check publications, NIH funding, hospital affiliations, industry payments and trial activity on one profile. Regulatory, quality and supplier risk Inspections, Form 483 observations, warning letters, recalls and import refusals attached to the firm, with firms that could not be matched shown as such. Translational science and biomarker strategy Each biomarker page labels its evidence by type, from FDA companion diagnostic to curated actionability to association, and links it to the drugs and trials that use it.

How the data is built

Collected, matched, and traceable to its sources

  1. Collected on a schedule

    Each public source is reloaded on its own schedule and kept dated, so history is never lost.

  2. Matched with caution

    Names are matched across sources only when the evidence is strong. When the evidence that two records are the same thing is weak, we keep them separate rather than risk merging two different companies.

  3. Linked to its sources

    Every page draws on the same matched data. On the page for a trial, drug, company or person, figures link to their source records. When a section on a condition or biomarker page was checked and found empty, the page says so.

What you can check before you pay

  • The sources. Every condition and biomarker page lists the sources behind it.
  • The gaps. When something is missing, condition and biomarker pages say so in a "Not on this page" list.
  • The price. Individual is $249 per seat per month and Team is $399 per seat per month, published on the pricing page.
  • The alternatives. A comparison with other tools, where each statement about another vendor links to that vendor's own page and carries the date it was checked.
  • The company. Pharma Observatory is a Scientist.com platform.

Published prices, bought on a card

Individual is $249 per seat per month and starts with a 14-day trial. Team is $399 per seat per month. Enterprise is quoted per deal. See all plans.

Questions

Questions buyers ask first

What is Pharma Observatory?

Pharma Observatory is a research tool for biopharma professionals. It matches public data on clinical trials, drugs, companies, investigators, trial sites, patents, funding and FDA enforcement, so that each drug, company or person has one page under every name the sources use. On those pages, figures link to their source records.

Where does the data come from, and can I check it?

The data comes from public biomedical and corporate sources, including ClinicalTrials.gov, PubMed, FDA, SEC filings and NIH. Each condition and biomarker page lists its sources, and on the page for a trial, drug, company or person, figures link to the registry entry, filing or publication behind them. Where a source carries license terms, the page shows the attribution.

How much does it cost, and can I cancel?

The Individual plan is $249 per seat per month and starts with a 14-day trial. A card is required, and the first charge is when the trial ends. The Team plan is $399 per seat per month, and Enterprise is quoted per deal. Prices are in US dollars and exclude tax. You can cancel your subscription yourself, in Stripe's billing portal.

Can I see anything before I start a trial?

Yes. The condition pages and biomarker pages are free to read without an account. They show trial counts by phase and year, sponsors, drugs and publications for a condition, and evidence by type for a biomarker. The rest of the product needs a plan.

How does it compare with other biopharma intelligence tools?

Pharma Observatory publishes a comparison with other tools. It covers published price, self-serve sign-up and trial terms. Each statement about another vendor comes from that vendor's own pages and carries a link and the date it was checked.

What does Pharma Observatory leave out?

It covers what public sources publish. Coverage of people and hospitals is fuller for the US, because the payment and hospital sources are US sources. Trial registries name a CRO on only part of their studies, and the CRO views show how many trials in any selection identify one. Patent Cliff sizes exposure by the revenue a company discloses and by US Medicare spend where none is disclosed. Condition and biomarker pages list what was looked for and found empty.

Who runs Pharma Observatory?

Pharma Observatory is a Scientist.com platform. Billing runs through Stripe, and questions go to support@scientist.com.

Run one real question through it this week

Pick a question you would normally answer with a registry search and a spreadsheet. The trial gives you 14 days to check the answer against what you already know.

See all plans

Individual plan, $249 per seat per month. Card required. Your first charge is when the trial ends.