ZoomInfo's verified intelligence (100M companies, 500M contacts, billions of buying signals) is now available from any terminal through the GTM.AI CLI, a command-line client for GTM.AI, the API and Model Context Protocol home for AI agents.
ZoomInfo (NASDAQ: GTM), the all-in-one AI GTM platform, today announced the GTM.AI CLI, a command-line client for ZoomInfo's go-to-market data. Developers, GTM engineers, and AI agents can now search and enrich companies and contacts, pull intent signals, Scoops, and news, run agentic research, and read their GTM context from any terminal. The CLI is the newest surface on GTM.AI, ZoomInfo's headless GTM context layer. GTM.AI exposes ZoomInfo's verified data graph and agentic orchestration through API and Model Context Protocol (MCP), so any platform, agent, or workflow can plug in. The CLI connects to the same hosted endpoint as the ZoomInfo MCP server, with the same credentials and the same credit consumption. Installation is one command through Homebrew or npm. Sign-in is OAuth in the browser, with no client ID or secret to paste. With this release, the GTM Context Graph is available anywhere a shell runs.
Key takeaways
The GTM.AI CLI is generally available. Install it with `brew install zoominfo/gtm-ai/gtm-ai-cli` or `npm install -g @zoominfo/gtm-ai-cli`. It is open source under the MIT license, with prebuilt binaries for macOS, Linux, and Windows.
One `gtm` command family covers the GTM data surface: companies, contacts, intent, Scoops, news, agentic research, and GTM context, with output in JSON, JSONL, CSV, YAML, or a table.
GTM.AI is the headless GTM context layer. The CLI joins dozens of completed integrations across CRMs, AI assistants, and MCP-native agents, with the same governance applied everywhere.
The GTM Context Graph behind GTM.AI maintains identity-resolved data on 100M companies, 500M contacts, and billions of signals, continuously updated and continuously queryable.
What is the GTM.AI CLI?
The GTM.AI CLI is a command-line client for ZoomInfo's go-to-market data. It searches and enriches companies and contacts, pulls intent signals, Scoops, and news, runs agentic research, and reads a customer's GTM context, all from the shell. Results return as JSON, JSONL, CSV, YAML, or a table, so output pipes cleanly into scripts, warehouse jobs, and agent workflows. The CLI is open source under the MIT license, with prebuilt binaries for macOS, Linux, and Windows.
How does the GTM.AI CLI work?
Installation is one command. On macOS and Linux, `brew install zoominfo/gtm-ai/gtm-ai-cli`. Anywhere Node runs, including Windows, `npm install -g @zoominfo/gtm-ai-cli`. Sign-in is OAuth in the browser: `gtm auth login` opens a browser window, and there is no client ID or secret to paste. Credentials are stored locally with owner-only file permissions.
From there, one `gtm` command family covers the data surface. `gtm companies` and `gtm contacts` handle search, enrichment, and similar-record discovery. `gtm intent`, `gtm scoops`, and `gtm news` pull signals. `gtm research` runs agentic account and contact research. `gtm gtm-context` reads and updates the customer's own GTM context. And `gtm raw` is the escape hatch for anything the named commands don't cover.
Under the hood, the GTM.AI CLI connects to the same hosted endpoint as the ZoomInfo MCP server. Same credentials, same governance, same credit consumption. A team that already uses ZoomInfo through MCP adds the CLI without a second integration.
What is GTM.AI, and why does it extend to the command line?
GTM.AI is ZoomInfo's headless GTM context layer. It exposes ZoomInfo's verified data graph and agentic orchestration through API and Model Context Protocol (MCP), so any tool, agent, or platform can plug in. The CLI is the newest surface on that layer, alongside dozens of completed integrations including Salesforce Agentforce, HubSpot Breeze, Microsoft Copilot, Gong, LeanData, Glean, Claude, ChatGPT, and Google Workspace.
GTM.AI has two layers and one governance plane. The bottom layer is the GTM Context Graph, which holds identity-resolved data on 100M companies, 500M contacts, and billions of signals. The middle layer is agentic orchestration, which lets agents read from the graph, act on it, and write back. The governance plane sits above both, applying access control, permissioning, data lineage, AI policy, and audit logging consistently across every surface that consumes GTM.AI. The CLI inherits the same posture as every other surface.
The reason a context layer extends to the command line is that GTM work moved there. GTM engineers build enrichment pipelines in shell scripts. Coding agents like Claude Code do their work in the terminal. Data teams schedule jobs that expect machine-readable output. The GTM.AI CLI puts the GTM Context Graph where that work already happens, in a form a script can pipe and an agent can call.
Why does the data layer matter at the command line?
About 70% of B2B contact data decays every year. A script that enriches a lead list against stale data automates the wrong answer at machine scale, and nobody is watching a cron job closely enough to catch it. The GTM.AI CLI reads the live GTM Context Graph on every call, so a pipeline built today returns the same verified answer the ZoomInfo platform itself would give.
The same argument applies to agents. An AI agent that pipes `gtm` output into the next step of a workflow compounds whatever error the data carries. Verified data at the first step keeps the whole chain grounded.
How is the GTM.AI CLI different from a generic data-vendor API?
One surface, not a second integration. The CLI connects to the same hosted endpoint as the ZoomInfo MCP server, sharing credentials and credit consumption. Teams standardize on GTM.AI once and reach it from the terminal, from MCP, or from the API.
Verified data layer through GTM.AI. Most data-vendor tooling wraps a static export. The GTM.AI CLI reads the GTM Context Graph, which is continuously refreshed and identity-resolved at the contact and account level.
Platform-level governance. Access control, permissioning, data lineage, AI policy, and audit logging apply to every `gtm` call, exactly as they apply to every other GTM.AI surface.
What does this mean for GTM engineers and RevOps teams?
Enrichment pipelines in one step. `gtm companies` and `gtm contacts` output pipes directly into the warehouse job or the CRM update, in the format the downstream system expects.
Agent-ready by default. The repository ships a Claude Code skill, and any coding agent that can run shell commands can query the GTM Context Graph through the CLI.
One context layer across the GTM stack. The CLI, the MCP server, the API, and every partner integration read the same GTM Context Graph and inherit the same governance.
FAQ: the GTM.AI CLI, ZoomInfo data, and GTM.AI
What is the GTM.AI CLI? The GTM.AI CLI is a command-line client for ZoomInfo's go-to-market data. It searches and enriches companies and contacts, pulls intent signals, Scoops, and news, runs agentic research, and reads GTM context from any terminal.
How do I install the GTM.AI CLI? On macOS and Linux, run `brew install zoominfo/gtm-ai/gtm-ai-cli`. On any system with Node, run `npm install -g @zoominfo/gtm-ai-cli`. Prebuilt binaries for macOS, Linux, and Windows are on the GitHub releases page.
What commands does the GTM.AI CLI include? The command families are `gtm lookup`, `gtm companies`, `gtm contacts`, `gtm intent`, `gtm scoops`, `gtm news`, `gtm research`, `gtm gtm-context`, `gtm feedback`, and `gtm raw`. Search, enrichment, similar-record discovery, and agentic research are covered by subcommands.
Is the GTM.AI CLI free? The CLI itself is open source under the MIT license, and search and lookup commands are free. Enrichment and agentic research require a ZoomInfo subscription with bulk data credits, consumed from the same pool as the ZoomInfo MCP server.
What is GTM.AI? GTM.AI is ZoomInfo's headless GTM context layer. It exposes ZoomInfo's verified data graph (100M companies, 500M contacts, billions of signals), agentic orchestration, and platform-level governance through API and Model Context Protocol (MCP), so any agent, platform, or workflow can plug in. GTM.AI powers dozens of completed integrations including Salesforce Agentforce, HubSpot Breeze, Microsoft Copilot, Gong, LeanData, Glean, Claude, ChatGPT, and Google Workspace.
Does the GTM.AI CLI use the Model Context Protocol (MCP)? Yes. The CLI connects to the same hosted endpoint as the ZoomInfo MCP server, with the same credentials and the same credit consumption. A team already using ZoomInfo through MCP adds the CLI without a second integration.
How does authentication work in the GTM.AI CLI? Sign-in is OAuth in the browser through `gtm auth login`, with no client ID or secret to paste. `gtm auth whoami` shows the active identity and `gtm auth logout` clears it. Tokens are stored locally with owner-only file permissions.
Does the GTM.AI CLI work with Claude Code and other coding agents? Yes. The repository ships a Claude Code skill, and any coding agent that can run shell commands can call the CLI directly. Structured output in JSON or JSONL makes the results machine-readable by default.
What output formats does the GTM.AI CLI support? JSON, JSONL, CSV, YAML, and a human-readable table, selected with the `-f` flag. A `--select` flag projects specific fields for tighter pipelines.
Does ZoomInfo have an API? Yes. GTM.AI is the API and Model Context Protocol home for ZoomInfo's verified GTM data. The GTM.AI CLI is a client on top of that same surface, built for terminals, scripts, and agents.
How does GTM.AI handle governance for the CLI? GTM.AI's platform layer applies access control, permissioning, data lineage, AI policy, and audit logging consistently across every surface that consumes it. Every `gtm` call inherits that posture, alongside ZoomInfo itself and every other GTM.AI integration.
Is the GTM.AI CLI available now? Yes. The GTM.AI CLI has been generally available since June 22, 2026, with the current release at v1.0.1.
Availability
The GTM.AI CLI is generally available today to ZoomInfo customers. Search and lookup are free. Enrichment and agentic research consume bulk data credits from an active ZoomInfo subscription. Documentation is at gtm.ai/docs/cli and the source is at github.com/Zoominfo/gtm-ai-cli.
About ZoomInfo
ZoomInfo (NASDAQ: GTM), the all-in-one AI GTM platform, enables sales, marketing, and customer success teams to execute their go-to-market strategy with confidence. Powered by the industry's most comprehensive B2B data, including more than 100 million companies, 500 million contacts, and billions of signals, ZoomInfo delivers the intelligence, automation, and integrations that modern revenue teams need to identify, engage, and convert their best buyers.
GTM.AI is ZoomInfo's headless GTM context layer. It is the API and Model Context Protocol home for AI agents, powering integrations across Salesforce Agentforce, HubSpot Breeze, Microsoft Copilot, Claude, ChatGPT, and dozens more.
Learn more at zoominfo.com and gtm.ai.
Media contact: Public Relations Team ZoomInfo PR@zoominfo.com
