---
title: "om-discovery"
description: "Hosted Om MCP plus the Om Discovery playbook for LULA, Discovery, Discovery Challenges, Hub, Diligence, Accessible Space, molecule orders, and ZenCloud scientific sessions."
canonical: https://agentpluginsdirectory.com/plugins/om-discovery
last-updated: 2026-10-21
---

# om-discovery
Hosted Om MCP plus the Om Discovery playbook for LULA, Discovery, Discovery Challenges, Hub, Diligence, Accessible Space, molecule orders, and ZenCloud scientific sessions.
- Slug: om-discovery
- Publisher: Om Therapeutics
- Repository: https://github.com/omtx-ai/omtx
- Manifest: plugin.json
- Version: 0.3.3
- License: Apache-2.0
- Category (editorial): other
- Skills: 1 (om-discovery)
- MCP servers: 1 (omtx)
- Stars: 0
- Repository created: 2025-07-11
- Repository last pushed: 2026-10-16
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/om-discovery
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What om-discovery does, in the publisher's words

Quick starts, tutorials, cookbooks, and the Om Discovery plugin for using Om from coding agents.

Use these guides to learn the Om API, work with the omtx Python SDK, run data-access workflows, launch diligence jobs, use Hub models and artifacts, and run LULA scoring with hosted Om workflows or local open-weight models.

Add the hosted Om MCP and the Om Discovery skill to Claude Code, Codex, Cursor, Copilot, Gemini, Grok, or another compatible agent:

- Quick Start: first successful API, SDK, and CLI workflows.
- Tutorials: step-by-step walkthroughs for data access, diligence jobs, and Hub artifact jobs.
- Cookbooks: applied recipes for common research and modeling tasks.
- Examples: runnable Python scripts.
- Notebooks: Colab-friendly LULA workflow notebooks.
- Query the Om API from curl, scripts, and notebooks.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/omtx-ai/omtx/HEAD/README.md

## MCP servers

- omtx: transport: streamable-http; url: https://agents.omtx.ai/mcp

Read from the plugin's own mcp.json. Environment variable names only, never values.