How to Use the Airparser MCP in Claude Code

Q: How do I configure Airparser with Claude Code?

Run claude mcp add --transport http airparser -- . Make sure all flags come before the server name. Your config saves to /.claude.json.

Q: How do I handle large document queues in Claude Code and Airparser?

Use the asynchronous tools. Have your script trigger parsedocumentasync so the CLI does not hang while the extraction engine processes the files.

Q: Can Claude Code read my extraction schemas?

Yes. It calls getinboxschema to pull the exact field definitions. You can pipe that output into jq to validate your data structures on the fly.

Pipe unstructured PDFs into your terminal. Connect Airparser to Claude Code for headless document extraction and automated JSON exports.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Airparser MCP to Claude Code

Create your Vinkius account to connect Airparser 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 Airparser with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Extract PDF data from the command line

Airparser turns messy documents into clean JSON payloads. You run a bash script that downloads daily reports from an FTP server. Claude Code grabs those files and executes `parse_document_sync`. It pipes the resulting structured data directly into your local Postgres instance. You never have to open a browser or click a button.

Manage exports with this MCP Server

Infrastructure as code means your webhooks should be configured automatically. Manual dashboard clicking has no place in a CI/CD pipeline. Your deployment script tells Claude Code to configure the environment. It runs `list_webhooks` to check existing routes. If the production callback is missing, it fires `create_webhook` to point the parsed data at your new server.

Trigger background extraction jobs

Processing a massive archive of legacy images takes time. You cannot afford to keep a synchronous terminal session open for hours. Claude Code kicks off the batch using `parse_document_async`. It records the job IDs and exits. A separate cron job runs later, calling `get_document_details` to pull down the finished JSON payloads when they are ready.

Setup guide

Set up Airparser 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 airparser-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http airparser-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 Airparser 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": {
    "airparser-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 Airparser. 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 Airparser 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 Airparser MCP in Claude Code

Run `claude mcp add --transport http airparser -- `. Make sure all flags come before the server name. Your config saves to `~/.claude.json`.

Run a prompt asking for your current setup. Claude Code executes `list_inboxes` and prints out the IDs and names directly to your standard output.

Use the asynchronous tools. Have your script trigger `parse_document_async` so the CLI does not hang while the extraction engine processes the files.

Yes. It calls `get_inbox_schema` to pull the exact field definitions. You can pipe that output into `jq` to validate your data structures on the fly.

Everything flows through a zero-trust V8 Isolate. Vinkius manages the auth with a single endpoint token. Your raw images and extracted text exist only in ephemeral memory during the transit process.

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