Deskpricer
About
Local HTTP pricing microservice for vanilla European and American equity options.
Explore
- Price + Greeks for single options and portfolios
- Implied volatility solver (Brent method via QuantLib)
- PnL attribution with delta, gamma, vega, theta, rho, vanna, volga
- XML-by-default output for seamless Excel integration
- Localhost-only binding (127.0.0.1) – no network exposure
- Four MCP tools: price_option, implied_volatility, pnl_attribution, portfolio_greeks
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
DeskpricerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Go from clean clone to a working pricing call in under 5 minutes:
python -m venv .venv
.venv\Scripts\activate
pip install -e ".[dev]"
If pip install fails on QuantLib, ensure you have a C++ compiler and CMake, or use a pre-built wheel. See docs/operator_guide.md for detailed steps.
pytest tests -v
```
---
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"deskpricer": {
"deskpricer": {
"command": "deskpricer-mcp",
"args": []
}
}
}
}McpServers
{
"deskpricer": {
"command": "deskpricer-mcp",
"args": []
}
}Local HTTP pricing microservice for vanilla European and American equity options. Designed for Excel WEBSERVICE + FILTERXML integration — no VBA, no Bloomberg terminal calls inside the service.
> Design intent: DeskPricer is a local-only tool for personal desk pricing and option analytics. It is not intended to be run or served as a public/server-style service. All design choices — localhost binding, no auth, no TLS, no rate limiting, XML-by-default — reflect this.
---
Use with AI Agents (MCP)
DeskPricer is available as an MCP server. Add it to Cursor, Claude Desktop, or any MCP-compatible agent:
pip install deskpricer
Published on PyPI: https://pypi.org/project/deskpricer/
Cursor — add to ~/.cursor/mcp.json:
{
"mcpServers": {
"deskpricer": {
"command": "deskpricer-mcp",
"args": []
}
}
}
Claude Desktop — add to claude_desktop_config.json:
{
"mcpServers": {
"deskpricer": {
"command": "deskpricer-mcp"
}
}
}
If deskpricer-mcp is not on your PATH, use the full path to the executable in your virtualenv.
Tools: price_option, implied_volatility, pnl_attribution, portfolio_greeks — same pricing engine as the HTTP API.
See docs/mcp_quickstart.md for full setup, conventions, and example prompts.
---
Quickstart
Go from clean clone to a working pricing call in under 5 minutes:
```powershell
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
