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

# Quickstart

> Deploy your first MCP tool in under 5 minutes.

This guide walks you through creating an MCP server, writing a tool, testing it in the dashboard, and connecting it to an AI client.

## Prerequisites

* An MCPCore account — [sign up free](https://app.mcpcore.io/register), no credit card required
* That's it. No local installs needed.

***

## Step 1 — Create a server

<Steps>
  <Step title="Open the dashboard">
    Go to [app.mcpcore.io](https://app.mcpcore.io) and navigate to **My Servers**.
  </Step>

  <Step title="Click New Server">
    Click the **New Server** button in the top-right corner.

    Fill in:

    * **Code** — a unique machine identifier (e.g. `github_tools`)
    * **Title** — a short, descriptive name (e.g. `GitHub Tools`)
    * **Subdomain** — your server's URL prefix (e.g. `github-tools`)
    * **Security mode** — start with **Public** for now; you can change it later
  </Step>

  <Step title="Save">
    Click **Create server**. You'll be taken to the server detail page, where you can see the endpoint URL and start adding tools.
  </Step>
</Steps>

***

## Step 2 — Write a tool

<Steps>
  <Step title="Go to Tools">
    On the server detail page, navigate to the **Tools** section and click **Create New Tool**.
  </Step>

  <Step title="Name your tool">
    Give your tool a name. Tool names become part of the MCP schema the AI sees — use lowercase snake\_case (e.g. `fetch_repo_stats`).
  </Step>

  <Step title="Add a parameter">
    Click **Add parameter** and add:

    * Name: `repo`
    * Type: `string`
    * Description: `GitHub repository in owner/repo format`
    * Required: yes
  </Step>

  <Step title="Write the code">
    Paste the following into the code editor:

    ```javascript theme={null}
    const res = await sdk.http({
      method: "GET",
      url: `https://api.github.com/repos/${params.repo}`,
    });

    const data = JSON.parse(res.body());

    return {
      stars:    data.stargazers_count,
      forks:    data.forks_count,
      language: data.language,
      topics:   data.topics,
    };
    ```
  </Step>

  <Step title="Save the tool">
    Click **Save**. The tool is now part of your server.
  </Step>
</Steps>

***

## Step 3 — Test it

<Steps>
  <Step title="Open the Run panel">
    With the tool selected, click the **Run** tab (or the play button in the editor toolbar).
  </Step>

  <Step title="Enter a parameter value">
    In the **repo** field, enter a real repository name — e.g. `mcpcoreio/docs`.
  </Step>

  <Step title="Click Run">
    Click **Run tool**. The response panel shows the JSON output within a second or two.
  </Step>
</Steps>

***

## Step 4 — Connect to an AI client

Copy the **Endpoint URL** from the server detail page and add it to your AI client:

<CardGroup cols={2}>
  <Card icon="robot" href="/connect/claude-desktop" title="Claude Desktop">
    Add MCPCore to your `claude_desktop_config.json`.
  </Card>

  <Card icon="code" href="/connect/cursor" title="Cursor">
    Add MCPCore via Cursor's MCP settings panel.
  </Card>

  <Card icon="wind" href="/connect/windsurf" title="Windsurf">
    Configure MCPCore in Windsurf's MCP config file.
  </Card>

  <Card icon="plug" href="/connect/overview" title="Any MCP client">
    Any client that supports the MCP spec works out of the box.
  </Card>
</CardGroup>

***

## What's next?

<CardGroup cols={2}>
  <Card icon="lock" href="/tools/secrets" title="Add secrets">
    Store API keys and reference them as `env.MY_KEY` — never hardcode credentials.
  </Card>

  <Card icon="shield" href="/servers/security-overview" title="Change security mode">
    Lock your server behind API Key or OAuth 2.0 before going to production.
  </Card>

  <Card icon="database" href="/tools/sandbox" title="Query a database">
    Use `sdk.db()` to connect to PostgreSQL, MySQL, or SQL Server.
  </Card>

  <Card icon="chart-bar" href="/observability/traffic-logs" title="Monitor traffic">
    See every request your server receives and how fast it responded.
  </Card>
</CardGroup>