GTM AI
GTM AIby ZoomInfo
Sign up

Codex

How to connect ZoomInfo MCP to OpenAI Codex: install the ZoomInfo plugin for the hosted server plus our GTM skills, or add it manually as a Custom MCP entry.

·Rowan BaileyRowan BaileySenior Director, Product

Overview

Codex is OpenAI's coding agent, powered by ChatGPT. ZoomInfo ships as a Codex plugin, so a single install gives Codex the hosted ZoomInfo MCP server and our GTM skills at once. If your Codex build doesn't expose plugins yet, add the MCP server by hand through the Custom MCP form. Both connect to the same endpoint and authenticate over OAuth.

Setup

Open the Plugin Directory

In the Codex app, open Plugins. In the CLI, run codex and then /plugins to open the plugin browser.

Find ZoomInfo

Search for ZoomInfo and open its listing.

Install

In the app, select Add to Codex. In the CLI, select Install plugin.

Connect your ZoomInfo account

Codex prompts you to sign in with ZoomInfo the first time it uses the server. Use your normal credentials or SSO. There's no developer app to register and no OAuth callback to host.

Verify the connection

Ask a question that needs ZoomInfo data, like "How many employees does Snowflake have?" The tool invocation appears inline.

Next - run your first session. Once ZoomInfo is connected, paste this into a new Codex session. It orients from your GTM context and only runs after you approve:

First GTM session
(Use the ZoomInfo MCP tools if available; otherwise use the GTM CLI. Use the tool schema or CLI help for supported commands.)

I just connected ZoomInfo. Help me complete the job below.

1. Read my saved business context with get_gtm_context, or the CLI equivalent. This read is free. Use the returned offerings, ICP, and role to frame the work. If context is missing, continue with the information we have. Save changes only if I explicitly ask; a first briefing does not require updating shared business context.

2. Prepare a connected account briefing. Ask me only which company or domain to brief if I haven't named one. Use the account and decision already in this conversation when available. Connect the account's available CRM history, including stage and status, with recent customer conversations and external buying signals. Use Account Research, and add Browse Engagements, Conversation Intelligence, or company signals when the briefing needs more evidence.
   Return a short briefing: where things stand, what changed, what remains unresolved, and one recommended next action. Cite the source and date for each material fact when returned. Distinguish the recommendation from the evidence.
   If the **Account Research** skill is available, use it for the briefing. Otherwise, use the available ZoomInfo tools described above.

3. Before calling a tool, check its schema or documented inputs rather than guessing at parameters. Ask only for missing inputs, in a single message, then name the tools and give a credit estimate if supported by their documentation. Label it as an estimate: actual charges depend on records and work done. Ask for approval once before paid research, then complete the selected job.

If a tool call comes back "No approval received" or a similar permission response, say so plainly, name the tool, and continue with the remaining steps. Don't retry the same call hoping for a different result, and don't invent an approval that didn't happen.

Include a source-coverage note of no more than 3 lines. Separate an unavailable or unauthorized source from a successful search with no matching records. If connection status is unknown, say so. Never infer "no customer history" from an empty result. Continue with available evidence and identify what is missing; use https://gtm.ai/guides/connect-customer-context for source setup.

Recommend CRM changes as drafts. Applying them requires an available, separately connected CRM workflow and my authorization. Do not claim a CRM update was made by ZoomInfo research tools.

New to ZoomInfo?

What the Plugin Adds

The plugin bundles the hosted MCP server at https://mcp.zoominfo.com/mcp plus a set of GTM skills, prewritten workflows that chain the underlying tools into finished output: account briefs, target lists, buying-committee maps, and lead scores. To run one explicitly, type @ in the Codex prompt and pick the skill. Otherwise describe the outcome and Codex selects the skill that fits.

For the full skill list and a deeper walkthrough, see the Codex setup guide.

Prefer the Manual Route? Custom MCP

If your Codex build doesn't expose plugins, or you want the server without the bundled skills, add it through the Custom MCP form:

Open Codex Settings

From inside Codex, go to Settings, then Custom MCP.

Add a new MCP server

Click Add and fill in:

  • Name: ZoomInfo
  • Transport: Streamable HTTP
  • URL: https://mcp.zoominfo.com/mcp

Save and authenticate

Click Save. Codex prompts you to sign in with ZoomInfo. Use your normal credentials or SSO.

Troubleshooting

You don't see ZoomInfo in the Plugin Directory: the listing may not have reached your directory search yet. Fall back to the Custom MCP route above.

Codex doesn't show a Custom MCP option: your Codex plan or workspace may not have Custom MCP enabled. Check with your OpenAI admin or workspace owner.

Authentication fails on sign-in: confirm you're using your personal ZoomInfo credentials, not a shared or admin-only account.

Codex doesn't see any ZoomInfo tools: for the plugin, confirm it shows as installed and enabled in /plugins. For Custom MCP, confirm the entry is listed and the URL is exactly https://mcp.zoominfo.com/mcp.

Credit errors on enrichment or research calls: MCP requires bulk data credits. Confirm with your ZoomInfo admin that your account has bulk credits enabled, not recurring monthly credits.

What's Next

For the full walkthrough including every GTM skill, see How to Add ZoomInfo to Codex. For the same setup in Anthropic's CLI, see Claude Code. For the full tool reference, see the MCP Tools documentation.

PreviousClaude CoworkNext Cursor