> ## Documentation Index
> Fetch the complete documentation index at: https://docs.clarvo.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Connect an MCP client

> Use Clarvo from Claude, ChatGPT, or another MCP client.

Connect Clarvo to an MCP client to work with your projects and candidate searches from a conversation.

## Connect

**1. Add Clarvo to your client**

In **Claude**, open **Customize → Connectors → Add → Add custom connector**. In
**ChatGPT**, open **Plugins** and add a custom MCP server. Other clients may call this
option a remote MCP server.

**2. Enter the connection details**

Name it **Clarvo** and use `https://hire.clarvo.ai/mcp` as the server URL. Choose
**Streamable HTTP** if asked for a transport, and **OAuth** for authentication. Leave
API key or token fields empty; you do not need to create a token.

**3. Authorize your workspace**

Click **Connect** in your MCP client, sign in to Clarvo, choose the workspace you
want to use, and approve the connection.

## Try it

For example, ask your client:

* *"Use Clarvo to create a project for a backend engineering role."*
* *"In that project, run a search for senior backend engineers in Helsinki with Go and Kubernetes experience."*
* *"Review the top candidates in detail."*

## Search a connected ATS

You can combine MCP with an [ATS integration](https://docs.clarvo.ai/integrations/ats.md) to search candidates
already in your organization's ATS. For example:

* *"Use Clarvo to search our connected ATS for a Databricks engineer in Helsinki with 5+ years of experience."*


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.