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

# Cursor

## Cursor

Connect Block Scholes to Cursor for AI-powered crypto derivatives analysis directly within your development environment. Cursor's Agent mode allows you to query data, run backtests, and generate visualisations using natural language.

{% hint style="info" %}
**Cursor Pro** (or higher) is required for reliable use of Agent features and MCP tool-calling.
{% endhint %}

### Step 1: Sign up for a Block Scholes account

Sign up for an account with Block Scholes at [Block Scholes Console](https://console.blockscholes.com/products/strategy-backtest).

### Step 2: Install Cursor

Download and install Cursor from [cursor.com/download](https://cursor.com/download). Launch the application and sign in or create an account.

### Step 3: Open a Project

1. Click **Open project**
2. Create or open a folder (e.g. `Block Scholes MCP`)

A dedicated project folder keeps your queries, outputs, and any generated files organised.

### Step 4: Add the MCP Server

The quickest way to add Block Scholes is via the Cursor deep link — click the badge below to install directly:

[![Install MCP Server in Cursor](https://cursor.com/deeplink/mcp-install-dark.svg)](cursor://anysphere.cursor-deeplink/mcp/install?name=Block%20Scholes\&config=eyJ0eXBlIjoic3NlIiwidXJsIjoiaHR0cHM6Ly9tY3AuYmxvY2tzY2hvbGVzLmNvbS9tY3AifQ==)

This will add the Block Scholes MCP server to your Cursor configuration automatically.

#### Manual Setup

If you prefer to configure manually:

1. Click the **settings cog** in the top-right corner
2. Navigate to **Cursor Settings**
3. Select **Tools & MCP** from the left-hand menu
4. Add a new MCP server with the following JSON configuration:

```json
{
  "mcpServers": {
    "Block Scholes": {
      "url": "https://mcp.blockscholes.com/mcp",
      "headers": {}
    }
  }
}
```

5. Save the file and return to the **Cursor Settings** tab

You should see **Block Scholes** listed under Installed MCP Servers.

### Step 5: Authenticate

Click **Connect** next to the Block Scholes server entry. A login window will appear — sign in with your Block Scholes account.

### Step 6: Start an Agent Chat

1. Click the **Toggle AI Pane** button (next to the settings cog) to open the chat interface
2. Select **Agent** mode
3. Choose **Opus 4.5** and above as the model for best results. Similarly, Cursor's Composer 2 is good for general use and does not consume as many tokens from your plan.

{% hint style="warning" %}
Use Opus 4.5 or above, or Composer 1.5 or above, only with our MCP Server.
{% endhint %}

### Step 7: Create the Block Scholes skill (Optional)

To keep outputs focused and consistent, create the shared [Block Scholes Skill](/mcp/block-scholes-skill.md).

That page includes the exact skill content and the Cursor-specific `/create-skill` flow.

### Verify the Connection

Test with a simple query in Agent mode:

> What is the current BTC 30-day implied volatility at the 25-delta level?

If the agent calls the Block Scholes `data_retrieval` tool and returns a result, the connection is working.


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.blockscholes.com/mcp/connecting-client/cursor.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.