Om MCP Use Cases
Practical ways teams use Om MCP for research, data retrieval, model execution, and workflow orchestration.
Om MCP is most useful when you want Om tools to stay inside the same Codex or Claude Code session. Instead of stopping to hand-build API requests, you can ask the client to use Om directly and keep the outputs in context for the next step.
Common workflows
| Goal | Tool families | What you get | Best for |
|---|---|---|---|
| Target triage | Diligence search, gather, synthesize | Citation-backed target and mechanism summaries | Early target review and scientific orientation |
| Data pull | Data Access catalog and binder retrieval | Binder and non-binder dataset export URLs for a protein | ML workflows, ranking, and downstream analysis |
| Job orchestration | Hub plus Jobs | Launch, status, wait, export, artifact URL retrieval | Operational use in coding agents and notebooks |
| Artifact handoff | Artifacts upload and finalize | Uploads and reusable artifact references | Keeping model inputs and outputs inside the same session |
Representative flows
Target-first discovery
Start with a target question, ask for the strongest evidence, then deepen only when the result warrants it.
- Search a gene or mechanism
- Gather a broader evidence set
- Synthesize or run deep diligence
Research to binders
Use the same session to move from a target thesis into protein selection and binder/non-binder dataset export retrieval.
- Inspect available proteins
- Ask for binders for a protein UUID
- Feed the exported dataset URLs into model or analytics workflows
Hub execution
Launch supported model workflows, then monitor and retrieve outputs without writing polling glue first.
- Submit runs
- Track status
- Retrieve exports and artifacts
Agentic workflow loops
Keep Om tools inside the same MCP harness so the next step can reason from the previous result.
- Research
- Decide
- Execute
- Retrieve outputs
What Om MCP is not
- It is not a replacement for direct API usage when you need production-grade orchestration or bespoke infrastructure.
- It is not limited to Diligence. The real surface includes Diligence, Data Access, Jobs, Artifacts, and Hub workflows.
- It is not tied to a single IDE. Any MCP-compatible harness that can connect to
https://agents.omtx.ai/mcpcan use the same Om tool surface.