> 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/codex.md).

# Connect Coresignal MCP to Codex

Connect Coresignal's MCP server to Codex to search, enrich, and export data from your development environment.

### What is Codex?

Codex is OpenAI’s coding agent. It runs in the terminal (Codex CLI), in IDEs through the Codex extension, and in the Codex desktop app. Codex can edit code, run commands, and connect to external tools and data through MCP servers, which makes it well-suited for data engineers, developers, and technical GTM teams. With the Coresignal MCP server connected, teams can search, enrich, and export Coresignal data directly in their development environment.

### How to connect Coresignal to Codex?

To start with, [sign up](https://dashboard.coresignal.com/sign-up) and create an account with Coresignal and ensure you have available credits, next follow these steps:

{% stepper %}
{% step %}
Run this in your terminal to add the server:

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

```
codex mcp add coresignal --url https://mcp.coresignal.com/mcp/v2
```

{% endcode %}
{% endstep %}

{% step %}
Check the connection by running:

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

```
codex mcp list
# coresignal: https://mcp.coresignal.com/mcp/v2 (HTTP) - / Connected
```

{% endcode %}
{% endstep %}
{% endstepper %}

### Verify connection

Once the server is connected, run a quick check:

1. `codex mcp list` shows coresignal as enabled
2. A free field discovery prompt returns results, for example: "**Which fields are available for employee records?**"
3. A search response shows the credits used for the request

### FAQ

<details>

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

Run `codex mcp add coresignal --url https://mcp.coresignal.com/mcp/v2` in your terminal. Then run `codex mcp list` to check that coresignal shows as connected.

</details>

<details>

<summary>Does Codex support remote (HTTP) MCP servers?</summary>

Yes. Coresignal connects to Codex as a remote server: you add it with the `--url` flag, and `codex mcp list` shows it as an HTTP connection.

</details>

<details>

<summary>What can I ask Codex to do with Coresignal data?</summary>

Anything you would ask in a chat, plus tasks that combine data with code. For example:&#x20;

{% prompt description="Find Series B SaaS companies in the U.S. and save the top 100 to data/companies.jsonl." %}

```markdown
Find Series B SaaS companies in the U.S. and save the top 100 to data/companies.jsonl.
```

{% endprompt %}

</details>

<details>

<summary>Do I need to set Coresignal up separately in the Codex CLI, IDE extension, and app?</summary>

No. The Codex CLI, IDE extension, and desktop app share the same `config.toml`, so a server added once works in all three. In the desktop app, start a new thread after signing in to load the Coresignal tools.

</details>

<details>

<summary>How do I remove Coresignal MCP from Codex?</summary>

Run `codex mcp remove coresignal` in your terminal. This deletes the server from `config.toml`, so it’s removed from the CLI, IDE extension, and desktop app.

</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/codex.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.
