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

GoalTool familiesWhat you getBest for
Target triageDiligence search, gather, synthesizeCitation-backed target and mechanism summariesEarly target review and scientific orientation
Data pullData Access catalog and binder retrievalBinder and non-binder dataset export URLs for a proteinML workflows, ranking, and downstream analysis
Job orchestrationHub plus JobsLaunch, status, wait, export, artifact URL retrievalOperational use in coding agents and notebooks
Artifact handoffArtifacts upload and finalizeUploads and reusable artifact referencesKeeping 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/mcp can use the same Om tool surface.