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

# Quickstart

> From nothing to an agent calling your local MCP server, in about two minutes.

You need a local MCP server running somewhere — a port, a `.test` hostname, a
Herd or Valet site. If you don't have one yet, any of the [official MCP SDK
examples](https://modelcontextprotocol.io) will do.

<Steps>
  <Step title="Install the CLI">
    ```bash theme={null}
    curl -fsSL https://heymcp.dev/install.sh | sh
    ```

    macOS and Linux, Intel and ARM. One static binary, checksum-verified.
    See [Installation](/installation) for what it does and how to control where
    it lands.
  </Step>

  <Step title="Sign in">
    ```bash theme={null}
    heymcp login
    ```

    Opens your browser once and signs the CLI in. Sign-in is GitHub only.
    If you don't have an account yet, this creates one.
  </Step>

  <Step title="Share your server">
    Point it at wherever your MCP server lives:

    ```bash theme={null}
    heymcp share localhost:8000
    ```

    `myapp.test`, `:8000`, `8000` and full URLs all work too — see
    [`heymcp share`](/cli/share).

    ```
    ●  myapp — https://amber-jetty.t.heymcp.dev/mcp
    ✓  handshake ok — 3 tools
    →  inspector: https://app.heymcp.dev/s/x7k2
    ```

    That first URL is yours to hand to an agent. The `handshake ok` line means
    HeyMCP already connected to your server as an MCP client and checked it
    over — if something is wrong, you'll see it here rather than finding out
    from a client that says nothing at all.
  </Step>

  <Step title="Hand the URL to an agent">
    The quickest client to prove it with is Claude Code, because it's the only
    one where the whole thing is a single command:

    ```bash theme={null}
    claude mcp add --transport http heymcp https://amber-jetty.t.heymcp.dev/mcp
    ```

    For everything else — Claude.ai, ChatGPT, Grok, Cursor, VS Code, Gemini —
    see [Connect a client](/clients/overview).
  </Step>

  <Step title="Watch it happen">
    Open the inspector URL the CLI printed. Every frame the agent exchanges
    with your server appears there live, folded into a readable timeline of
    attempts rather than raw JSON-RPC.

    Ask the agent to use one of your tools and watch the row appear.
  </Step>
</Steps>

## What to do next

<CardGroup cols={2}>
  <Card title="Read the handshake report" icon="stethoscope" href="/concepts/the-probe">
    The `handshake ok` line is a summary. The full report lists everything
    about your schemas that will bite with some client.
  </Card>

  <Card title="Keep the URL stable" icon="link" href="/concepts/urls-and-paths">
    Your account's slug doesn't change between runs, so a connector you add
    today still works tomorrow.
  </Card>

  <Card title="Lock the tunnel down" icon="lock" href="/security/authentication">
    A public URL is public. `--bearer` puts a token in front of it.
  </Card>

  <Card title="Nothing showed up?" icon="circle-question" href="/troubleshooting">
    Most MCP client failures are silent. This page is the playbook.
  </Card>
</CardGroup>