How to Use the Extracta MCP in Claude Code

Q: How do I add the Extracta MCP Server to Claude Code?

Run claude mcp add --transport http extracta -- in your terminal. This command adds the MCP configuration to your /.claude.json file, making all ten tools instantly available.

Q: Can I pipe Extracta output to other CLI tools in Claude Code?

Yes. You can ask Claude Code to run getresults or getbatchresults and redirect the resulting JSON output to files, databases, or command-line utilities like jq.

Q: How does Claude Code handle Extracta document classification?

The CLI agent uses createclassification to set up categories, then queries getclassificationresults to determine document types, letting you script automated routing rules in your terminal.

Pipe structured document data directly into your terminal workflows using Extracta and 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 Extracta MCP to Claude Code

Create your Vinkius account to connect Extracta 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 Extracta with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Headless Document Pipelines in Claude Code

Run complex document processing jobs straight from your shell. Claude Code uses `upload_file_url` to send files to the extraction engine and pipes the output of `get_results` directly into your terminal utilities or databases. Because it operates entirely in the CLI, you can combine this MCP Server with standard bash commands to automate high-volume document ingestion. It is ideal for SREs and backend developers who avoid heavy graphical interfaces.

Scriptable Schema Management via CLI

Manage your extraction setups without opening a browser. Claude Code uses `create_extraction` to register new document schemas and `update_extraction` to patch existing mapping rules directly from your terminal session. If you need to audit your active configurations, the CLI agent runs `view_extraction` to output the exact JSON structure. This makes it easy to track schema versions and commit changes to your git repositories.

Automated Document Routing in Shell Scripts

Integrate document sorting into your cron jobs. Claude Code uses `create_classification` to define file categories and `get_classification_results` to inspect incoming PDFs or images, letting your scripts route files based on their type over a fast MCP channel. If you need to clean up old pipelines, the agent calls `delete_extraction` to remove obsolete endpoints. It gives you full control over your document infrastructure using simple, headless commands.

Setup guide

Set up Extracta 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 extracta-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http extracta-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 Extracta 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": {
    "extracta-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 Extracta. 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 Extracta 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 Extracta MCP in Claude Code

Run `claude mcp add --transport http extracta -- ` in your terminal. This command adds the MCP configuration to your `~/.claude.json` file, making all ten tools instantly available.

Yes. You can ask Claude Code to run `get_results` or `get_batch_results` and redirect the resulting JSON output to files, databases, or command-line utilities like jq.

The CLI agent uses `create_classification` to set up categories, then queries `get_classification_results` to determine document types, letting you script automated routing rules in your terminal.

Absolutely. Since Claude Code runs entirely in the terminal, you can execute document extraction scripts using this configuration inside GitHub Actions, Docker containers, or remote SSH sessions.

The MCP Server runs in a zero-trust V8 sandbox hosted by Vinkius. Your raw document text and schema metadata are processed ephemerally, ensuring that sensitive terminal-based pipelines remain completely private.

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