Nullary - Negative Results Intelligence For Drug Discovery
About
Nullary is a hosted MCP server that lets AI agents query measured negative results from drug discovery: inactive compounds, failed selectivity panels, terminated clinical trials, failed CRISPR screens, antibody developability failures, and more — each result carrying full provena
Details
- Author
- nullary-ai
- Downloads
- 228
- Categories
- Other
Jump to
- Queries failed compounds, trials, and screens by target
- Supports small molecule, CRISPR, antibody, peptide modalities
- Includes PROTAC, clinical trial, and other modalities
- Every response cites its source
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Nullary - Negative Results Intelligence For Drug DiscoveryCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Interact by asking natural language questions about negative results in drug discovery, such as "What's failed against EGFR?" or "Which kinase inhibitors were inactive in ChEMBL?" The README does not specify installation or configuration steps.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"nullary - negative results intelligence for drug discovery": {
"nullary": {
"url": "https://mcp.nullary.ai/mcp"
}
}
}
}McpServers
{
"nullary": {
"url": "https://mcp.nullary.ai/mcp"
}
}What you can ask
- "What's failed against EGFR?" — failed compounds, trials, and screens for a target, across modalities
- "Which kinase inhibitors were inactive in ChEMBL?"
- "Show terminated Phase 2 oncology trials and why they stopped"
- "Failed CRISPR knockouts for TP53"
Tools are organized by modality (small molecule, CRISPR, antibody, peptide, PROTAC, clinical trial, …); every response cites its source.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
