How to Use the Alegra MCP in Claude Code

Q: What's the command to connect the Alegra server to Claude Code?

It's a single line in your terminal. Run claude mcp add --transport http alegra -- . You can then verify the connection is active by running claude mcp list.

Pipe live Alegra ERP data directly into your shell scripts and CI/CD pipelines with Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Alegra MCP to Claude Code

Create your Vinkius account to connect Alegra to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Alegra with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Checks in Your CI Pipeline

This MCP Server lets you add business logic checks to your deployment process. For example, before deploying a new e-commerce feature, you can have a GitHub Action call Claude Code to run a script that confirms key products are in stock using `list_inventory_items`. If stock is low, the build fails. You can script checks against any of the Alegra tools. Use `list_invoices` to ensure the billing system is responsive or `list_contacts` to validate a service connection. It’s a simple way to make your CI pipeline aware of real-world business status.

Run Business Reports from the Terminal

The Alegra tools are fully accessible from your command line with Claude Code. You can write a simple shell script to generate a daily sales report by calling `list_invoices` with today's date and piping the output to a file or another command. It’s perfect for cron jobs. Combine tools for more complex reports. For instance, get a list of recent payments with `list_payments`, then use `get_contact_details` in a loop to append the payer's name to each line. Since it's all in the terminal, you can use `grep`, `awk`, and `sed` to format the output exactly how you want it.

Manage Alegra via SSH or Cron with Claude Code

With this MCP server, you don't need a UI to manage your business operations. You can SSH into a server and use Claude Code to create a new sales invoice with `create_invoice` or add a new provider with `create_contact`. The output is clean text, ideal for headless environments. This is useful for building custom integrations or bots. You could have a script that listens to an event queue and, upon receiving a message, uses Claude Code to query for estimate details with `get_estimate_details`. It's a direct, scriptable interface to your Alegra account.

Setup guide

Set up Alegra 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

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

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see alegra-mcp with a green status indicator.
3

Start using tools

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

Terminal

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

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Alegra MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "alegra-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Alegra. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

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

Connect Alegra now

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 Alegra MCP in Claude Code

Once the Alegra MCP server is connected, you can call its tools in a script. For example: `claude run 'list all invoices from last month' --server alegra | grep 'Overdue'`. The output is standard text, so you can pipe it to any other command-line tool.

It provides plain text output by default, which is designed for scripting and piping. This makes it easy to integrate with standard Unix tools like `jq`, `awk`, or `grep` to parse and manipulate the data from Alegra.

It's a single line in your terminal. Run `claude mcp add --transport http alegra -- `. You can then verify the connection is active by running `claude mcp list`.

Yes. Claude Code is a self-contained binary, so you can easily add it to a Docker image. This lets you run Alegra tool calls like `create_invoice` or `list_inventory_items` as part of a containerized workflow or a Kubernetes Job.

All requests are stateless. When your script calls an Alegra tool, the data—like invoice or contact information—is processed in a dedicated V8 Isolate sandbox on Vinkius that is destroyed after execution. Your endpoint token authenticates the request, and no sensitive data is logged or persisted.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript