
Cortellis MCP Server
Enables searching for drugs and exploring ontology terms in the Cortellis database, providing access to comprehensive drug development status information with structured JSON responses.
Tools
get_drug_swot
Return SWOT analysis complementing chosen drug record for a submitted drug identifier from Cortellis API
get_drug_financial
Return financial commentary and data (actual sales and consensus forecast) for a submitted drug identifier from Cortellis API
get_company
Return the entire company record with all available fields for a given identifier from Cortellis API
search_drugs
Search for drugs in the Cortellis database. If the amount of drugs returned do not match with the totalResults, ALWAYS use the offset parameter to get the next page(s) of results.
explore_ontology
Explore the ontology or taxonomy terms in the Cortellis database
get_drug
Return the entire drug record with all available fields for a given identifier from Cortellis API
search_companies
Search for companies in the Cortellis database. If the amount of companies returned do not match with the totalResults, ALWAYS use the offset parameter to get the next page(s) of results.
README
Cortellis MCP Server
MCP Server for searching drugs and exploring ontology terms in the Cortellis database.
Installation
# Using npm
npm install @uh-joan/cortellis-mcp-server
Quick Start
- Set up your environment variables:
CORTELLIS_USERNAME=your_username
CORTELLIS_PASSWORD=your_password
USE_HTTP=true # Optional: run as HTTP server
PORT=3000 # Optional: specify port for HTTP server
- Run the server:
# As MCP server
npx cortellis-mcp-server
# As HTTP server
USE_HTTP=true PORT=3000 npx cortellis-mcp-server
Tools
-
search_drugs
- Search for drugs in the Cortellis database
- Optional Inputs:
query
(string) - Raw search querycompany
(string) - Company developing the drugindication
(string) - Active indications (e.g., obesity)action
(string) - Target specific action (e.g., glucagon)phase
(string) - Development status:- Supports both short and descriptive formats:
- Short format: S, DR, CU, C1-C3, PR, R, L, OL, NDR, DX, W
- Descriptive format: "Phase 1 Clinical", "Phase 2 Clinical", "Phase 3 Clinical", "Launched", etc.
- Supports OR/AND operators: "C2 OR C3" or "Phase 2 Clinical OR Phase 3 Clinical"
- Examples:
phase: "C3"
(short format)phase: "C2 OR C3"
(short format)phase: "Phase 2 Clinical OR Phase 3 Clinical"
(descriptive format)phase: "C2 AND C3"
(using AND operator)
- Status codes:
- S: Suspended
- DR: Discovery/Preclinical
- CU: Clinical (unknown phase)
- C1-C3: Phase 1-3 Clinical
- PR: Pre-registration
- R: Registered
- L: Launched
- OL: Outlicensed
- NDR: No Development Reported
- DX: Discontinued
- W: Withdrawn
- Supports both short and descriptive formats:
phase_terminated
(string) - Last phase before NDR/DX- Supports same formats and operators as
phase
- Examples:
phase_terminated: "C2 OR CR"
(short format)phase_terminated: "C2"
(short format)phase_terminated: "Phase 2 Clinical"
(descriptive format)phase_terminated: "C2 OR C3"
(multiple phases)
- Supports same formats and operators as
technology
(string) - Drug technology (e.g., small molecule)drug_name
(string) - Name of the drugcountry
(string) - Country of developmentoffset
(number) - For pagination
- Returns: JSON response with drug information and development status
-
explore_ontology
- Explore taxonomy terms in the Cortellis database
- Optional Inputs (at least one required):
term
(string) - Generic search termcategory
(string) - Category to search withinaction
(string) - Target specific actionindication
(string) - Disease/conditioncompany
(string) - Company namedrug_name
(string) - Drug nametarget
(string) - Drug targettechnology
(string) - Drug technology
- Returns: JSON response with matching taxonomy terms
-
get_drug
- Return the entire drug record with all available fields for a given identifier
- Required Input:
id
(string) - Drug Identifier
- Returns: JSON response with complete drug record
-
get_drug_swot
- Return SWOT analysis complementing chosen drug record
- Required Input:
id
(string) - Drug Identifier
- Returns: JSON response with SWOT analysis for the drug
-
get_drug_financial
- Return financial commentary and data (actual sales and consensus forecast)
- Required Input:
id
(string) - Drug Identifier
- Returns: JSON response with financial data and commentary
-
get_company
- Return the entire company record with all available fields for a given identifier
- Required Input:
id
(string) - Company Identifier
- Returns: JSON response with complete company record
-
search_companies
- Search for companies in the Cortellis database
- Optional Inputs:
query
(string) - Raw search querycompany_name
(string) - Company name to search forhq_country
(string) - Company headquarters countrydeals_count
(string) - Count for all distinct deals where company is principal/partner- Format: '<20' for less than 20 deals
- Format: '20' or '>20' for greater than 20 deals (default behavior)
indications
(string) - Top 10 indication termsactions
(string) - Top 10 target-based action termstechnologies
(string) - Top 10 technologies termscompany_size
(string) - The size of a company based on market capitalization in billions USD- Format: '<2' for less than $2B
- Format: '2' or '>2' for greater than $2B (default behavior)
status
(string) - Highest status of linked drugsoffset
(number) - For pagination
- Returns: JSON response with company information
Features
- Direct access to Cortellis drug database
- Comprehensive drug development status search
- Ontology/taxonomy term exploration
- Detailed drug information retrieval
- SWOT analysis for drugs
- Financial data and forecasts
- Structured JSON responses
- Pagination support for large result sets
HTTP API Endpoints
When running in HTTP mode (USE_HTTP=true), the following REST endpoints are available:
-
POST /search_drugs
- Search for drugs with optional filters
- Body: JSON object with search parameters (see
search_drugs
tool inputs)
-
POST /explore_ontology
- Search taxonomy terms
- Body: JSON object with search parameters (see
explore_ontology
tool inputs)
-
GET /drug/:id
- Get complete drug record by ID
- Parameters:
id
: Drug identifier
-
GET /drug/:id/swot
- Get SWOT analysis for a drug
- Parameters:
id
: Drug identifier
-
GET /drug/:id/financial
- Get financial data and forecasts for a drug
- Parameters:
id
: Drug identifier
-
GET /company/:id
- Get complete company record by ID
- Parameters:
id
: Company identifier
-
POST /search_companies
- Search for companies with optional filters
- Body: JSON object with search parameters (see
search_companies
tool inputs)
Setup
Environment Variables
The server requires Cortellis API credentials:
CORTELLIS_USERNAME=your_username
CORTELLIS_PASSWORD=your_password
Installing on Claude Desktop
Before starting make sure Node.js is installed on your desktop for npx
to work.
-
Go to: Settings > Developer > Edit Config
-
Add the following to your
claude_desktop_config.json
:
{
"mcpServers": {
"cortellis": {
"command": "npx",
"args": [
"-y",
"@uh-joan/cortellis-mcp-server"
],
"env": {
"CORTELLIS_USERNAME": "your_username",
"CORTELLIS_PASSWORD": "your_password"
}
}
}
}
- Restart Claude Desktop and start exploring drug development data!
Build (for devs)
git clone https://github.com/uh-joan/cortellis-mcp-server.git
cd cortellis-mcp-server
npm install
npm run build
For local development:
# Copy example environment file
cp .env.example .env
# Edit .env with your credentials
vim .env # or use your preferred editor
# Start the server
npm run start
Docker
docker build -t cortellis-mcp-server .
docker run -i --env-file .env cortellis-mcp-server
License
This MCP server is licensed under the MIT License.
Disclaimer
Cortellis™ is a commercial product and trademark of Clarivate Analytics. This MCP server requires valid Cortellis API credentials to function. To obtain credentials and learn more about Cortellis, please visit Clarivate's Cortellis page.
This project is not affiliated with, endorsed by, or sponsored by Clarivate Analytics. All product names, logos, and brands are property of their respective owners.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.
Versioning
We use SemVer for versioning. For the versions available, see the tags on this repository.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.