Om MCP Overview

Pick your agent harness and connect the hosted Om MCP. Score proteins, start Discovery, and use Om tools from Claude, Codex, Cursor, VS Code, Copilot, Gemini, Grok, or another remote MCP client.

Om MCP is the hosted MCP interface for Om. Pick the agent you already use, add https://agents.omtx.ai/mcp, complete the client OAuth flow, and keep Om tools in the same session.

Pick your agent harness to use Om

Setup in four steps

1

Pick your agent

Use Claude, Codex, Cursor, VS Code, Copilot, Gemini, Grok, or another remote MCP client.

2

Add the hosted Om MCP

Point the client at https://agents.omtx.ai/mcp.

3

Authenticate with OAuth

Complete the client’s browser login. Om asks for email only.

4

Restart and verify

Ask for om_status, pricing_get, or credits_get to confirm the server is attached.

Hosted server

SettingValueNotes
MCP URLhttps://agents.omtx.ai/mcpHosted Om MCP endpoint for remote MCP clients.
Transportstreamable HTTPMCP clients should connect over HTTPS to the /mcp route.
AuthenticationOAuth 2.0Hosted Om MCP expects the client’s remote-MCP OAuth flow rather than manual API-key headers.
Direct API authx-api-key or Authorization: Bearer <OAuth access token>Direct /v2/* API routes still support API-key auth as the canonical external path. Hosted MCP startup uses OAuth.

Verified versus standard MCP config

Claude and Codex are the Om-tested login paths. Cursor desktop, VS Code, Copilot, Gemini, Grok, and other remote MCP clients use the same hosted URL. Cursor on the web and Cursor Agents use a hosted callback Om has not enabled yet. If a client cannot complete browser OAuth, use the Om API with an API key.

Diligence

Search, gather, crawl, synthesize, and run deep diligence from the same session.

  • Fast target triage
  • Claim-backed research workflows
  • Citation-oriented outputs

Data Access

Find Generated Data available to your account and retrieve binder and non-binder exports for a protein.

  • Account-scoped data discovery
  • Signed binder and non-binder exports
  • Model-ready Generated Data pulls

Jobs + Artifacts

Launch work, wait on completion, export results, and retrieve artifacts without leaving the session.

  • Polling and wait helpers
  • Artifact upload and finalize
  • Signed download URLs

Hub

Launch supported model workflows and inspect execution state directly.

  • Submit runs
  • Track job progress
  • Pull outputs into downstream work

System

Check health, pricing, profile, and Wallet Credits from the same client session.

  • om_status
  • pricing_get
  • credits_get
  • users_profile

Good first prompts

  • Run om_status to verify the MCP is attached.
  • Run pricing_get to inspect the current pricing manifest.
  • Ask Om MCP which Generated Data entries are available in Data Access.
  • Run diligence_search or diligence_gather on a target you already care about.

Typical MCP workflow

1

Ask the question

Start with a target, protein UUID, job goal, or workflow question inside your MCP client.

2

Use Om tools directly

Run Diligence, Data Access, Jobs, Artifacts, or Hub tools without building request glue first.

3

Keep the result in-session

Let the next step use the returned evidence, data export URLs, job IDs, or artifact URLs immediately.

4

Move into the API when needed

Use the direct API only when you need orchestration beyond the MCP session.

Security and approval

Hosted Om MCP is an authenticated OAuth tool surface. Keep manual tool approval on in your MCP client, authorize only the account/workspace you intend to use, and treat the connected session like live account access.