> For the complete documentation index, see [llms.txt](https://docs.coresignal.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.coresignal.com/integrations/coresignal-mcp/antigravity-cli.md).

# Connect Coresignal MCP to Antigravity CLI

Connect Antigravity CLI to Coresignal MCP to search, enrich, and export data from your terminal.

### What is Antigravity CLI?

Antigravity CLI is Google’s terminal-based coding agent and the successor to Gemini CLI. It uses the same agent setup as the Antigravity IDE and desktop app. Antigravity CLI can read and edit code, run commands, and connect to external tools and data through MCP servers.

With Coresignal MCP connected, developers, data engineers, and technical teams can search, enrich, and export Coresignal data from their development environment and use the results in scripts, pipelines, and applications.

### How to connect Antigravity CLI to Coresignal?

{% stepper %}
{% step %}
Make sure you have a Coresignal account with available credits and [Node.js](https://nodejs.org/en/download) installed. We recommend Node.js v24 for optimal compatibility and performance with Coresignal MCP, the version we validate and support.
{% endstep %}

{% step %}
Open `~/.gemini/config/mcp_config.json` file in a text editor. If a file doesn’t exist, create it.
{% endstep %}

{% step %}
Add the following file under `mcpServers`:

{% code lineNumbers="true" expandable="true" %}

```
{
  "mcpServers": {
    "coresignal": {
      "command": "npx",
      "args": ["-y", "mcp-remote@latest", "https://mcp.coresignal.com/mcp/v2"]
    }
  }
}
```

{% endcode %}
{% endstep %}

{% step %}
Save the file and start Antigravity CLI by running `agy`. If it was already running, restart it. When your browser opens the Coresignal dashboard, sign in and approve access.
{% endstep %}

{% step %}
Check the connection by typing `/mcp` in the Antigravity CLI session. **coresignal** should be listed as connected.
{% endstep %}
{% endstepper %}

### FAQ

<details>

<summary>How do I add an MCP server to Antigravity CLI?</summary>

Open or create `~/.gemini/config/mcp_config.json`. Under `mcpServers`, add a coresignal entry running `npx -y mcp-remote@latest https://mcp.coresignal.com/mcp/v2`. Save, start or restart `agy`, sign in when the browser opens, and confirm with `/mcp`.&#x20;

</details>

<details>

<summary>Can I use Coresignal with Zapier and Antigravity CLI?</summary>

Yes. Connect Zapier’s MCP server to Antigravity CLI, then add Coresignal as an app in [Zapier](https://docs.coresignal.com/integrations/zapier.md) with your Coresignal API key from the dashboard. You can then search, enrich, and collect Coresignal data through Zapier.

</details>

<details>

<summary>Do Antigravity CLI and the Antigravity IDE share MCP servers?</summary>

Antigravity CLI uses the same agent setup as the Antigravity IDE and desktop app. Thus, the MCP configuration in `~/.gemini/config/mcp_config.json` applies across them.

</details>

<details>

<summary>Which Node.js version does Coresignal MCP need in Antigravity CLI?</summary>

Node.js v24 is recommended. It is the version Coresignal validates and supports for the best compatibility and performance. Node.js is required because the connection runs through `npx` and `mcp-remote`.

</details>

<details>

<summary>How many credits does Coresignal MCP use in Antigravity CLI?</summary>

Credit usage depends on the task you want to perform. Field discovery and reading delivered files are free. Full profile pulls cost 1–20 credits per record. See our [pricing](https://docs.coresignal.com/pricing/).

</details>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.coresignal.com/integrations/coresignal-mcp/antigravity-cli.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
