Om MCP Quickstart

Connect your MCP client to the hosted Om MCP with OAuth and run your first workflow.

5-step setup

1

Use an OAuth-capable client

Use a client that supports remote MCP OAuth for hosted HTTP servers.

Codex or Claude Code
2

Use the hosted MCP URL

Point your MCP client at the hosted Om MCP endpoint.

https://agents.omtx.ai/mcp
3

Add client config

Add the hosted server to your client, then complete the OAuth login flow.

4

Restart your MCP client

MCP clients need a restart before newly added servers appear in the tool list.

5

Run a smoke test

Ask for `om_status`, `pricing_get`, or `datasets_catalog` before moving into deeper workflows.

Remote connection details

FieldValueWhy it matters
Server URLhttps://agents.omtx.ai/mcpThis is the hosted MCP endpoint clients connect to.
Codex authcodex mcp login omtxCodex can complete remote MCP OAuth after you add the server.
Claude Code auth/mcpClaude Code completes remote MCP OAuth from the in-app MCP menu after the server is added.

No local repo setup required

Om MCP is a hosted remote MCP server. You do not need the Om repo, a local Python process, or a manual MCP launcher to use it. You only need the hosted MCP URL and a client that supports OAuth for remote MCP.

codex mcp addBash
codex mcp add omtx --url https://agents.omtx.ai/mcp
codex mcp login omtx

Smoke-test prompts

  • Run om_status and tell me if the Om MCP is healthy.
  • Run pricing_get and summarize the pricing manifest.
  • Run datasets_catalog and show me the top-level dataset families I can access.
  • Run diligence_search for KRAS and return the highest-signal findings.