Vinkius
Pennylane logo
Vinkius
Vinkius runs on Claude Code

How to Use the Pennylane MCP in Claude Code

Run headless Pennylane workflows directly from your terminal with Claude Code to manage invoices, suppliers, and estimates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Pennylane MCP on Cursor AI Code Editor MCP Client Pennylane MCP on Claude Desktop App MCP Integration Pennylane MCP on OpenAI Agents SDK MCP Compatible Pennylane MCP on Visual Studio Code MCP Extension Client Pennylane MCP on GitHub Copilot AI Agent MCP Integration Pennylane MCP on Google Gemini AI MCP Integration Pennylane MCP on Lovable AI Development MCP Client Pennylane MCP on Mistral AI Agents MCP Compatible Pennylane MCP on Amazon AWS Bedrock MCP Support
MCP Servers — Included with Plan
Vinkius runs on Claude Code

Connect Pennylane MCP to Claude Code

Create your Vinkius account to connect Pennylane to Claude Code — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Key Capabilities

Headless Client Ledger Management

The integration uses `list_customers` and `get_customer_details` to let you manage your client ledger directly from your Claude Code terminal. You can inspect specific accounts in Pennylane without leaving your shell. It is built for speed, allowing you to script entire Pennylane accounting checks from a single Claude Code terminal session.

Command-Line Reconciliation via MCP Server

This MCP Server exposes `list_customer_invoices` and `get_customer_invoice_details` to let you audit Pennylane billing data from the command line using Claude Code. When you need to drill down into a specific transaction, Claude Code calls the tool to dump the VAT rates and line items. It is the fastest way to debug Pennylane billing issues without opening a browser.

Terminal-Driven Supplier Audits

The server uses `list_suppliers` and `list_supplier_invoices` to manage your vendor expenses directly inside your Claude Code terminal. If you need to verify a vendor's details in Pennylane, the Claude Code agent runs `get_supplier_details` to fetch their tax info. You can automate these checks in your local shell scripts to monitor Pennylane expenses on a schedule.

Setup guide

Set up Pennylane MCP in Claude Code

Prerequisites

  • Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Run the add command

    Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.

  2. 2

    Verify the connection

    Start a Claude Code session and type /mcp to list connected servers. You should see pennylane-mcp with a green status indicator.

  3. 3

    Start using tools

    Ask Claude Code something like "Check my latest Pennylane transactions." It will automatically discover and invoke the available Pennylane tools.

Terminal
claude mcp add --transport http pennylane-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Pennylane MCP in Claude Code

Run the `claude mcp add` command with the transport flags and the server URL. Claude Code will load the thirteen tools, allowing you to manage invoices and customers directly from your terminal.
Yes, Claude Code operates entirely in the terminal, meaning you can take outputs from tools like `list_customers` and format or save them using standard shell commands.
Yes, you can instruct the agent to run `list_estimates` and cross-reference them with your local database records to update the status of your French accounting pipeline.
This server supports stdio, HTTP, and SSE transports. You can configure the connection in your local configuration file depending on your network environment.
The server runs in an isolated V8 sandbox on Vinkius, and your API credentials stay stored in your local terminal configuration. Your invoices, customer lists, and supplier records are never exposed to external logging services.

Start using the Pennylane MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 13 tools

We've already built the connector for Pennylane. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 13 tools are live and waiting. You're up and running in seconds.

Vinkius runs on Claude Claude
Vinkius runs on ChatGPT ChatGPT
Vinkius runs on Cursor Cursor
Vinkius runs on Gemini Gemini
Vinkius runs on Windsurf Windsurf
Vinkius runs on VS Code VS Code
Vinkius runs on JetBrains JetBrains
Vinkius runs on Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.