How to Use the Docparser MCP in Claude Code

Q: How do I install the Docparser MCP Server in Claude Code?

Run the command claude mcp add --transport http docparser-mcp -- in your terminal. This registers the server and makes all ten document parsing tools available in your CLI session.

Q: How does Claude Code debug failed extractions in Docparser?

The agent calls listfaileddocumentextractions to find broken runs. The agent uses the MCP tool definitions to call the API and pull the layout details using getparserdetails to show you exactly why the rules failed to match.

Pipe structured PDF data straight to your terminal and automate document pipelines using Claude Code and Docparser.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Docparser MCP to Claude Code

Create your Vinkius account to connect Docparser 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 Docparser with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipe extracted PDF data to terminal tools

The `get_document_extraction_results` tool dumps raw JSON data directly into your terminal so you can pipe the output into jq or grep. Claude Code brings Docparser straight to your CLI workflows. You don't need to open a browser to check if your pipeline is running smoothly. The agent uses `list_recent_extractions` to print a clean ASCII table of your latest processed documents directly in your shell session.

Audit document pipelines via Claude Code CLI

Claude Code runs `quick_parser_health_audit` to instantly expose which templates are failing or lagging right inside your SSH session. Connecting this MCP Server to Claude Code gives you instant visibility into your ingestion pipeline. If a parser is failing, the agent executes `list_failed_document_extractions` to isolate the broken files. It then displays the configuration details using `get_parser_details` so you can diagnose the rule mismatch on the fly.

Script bulk document tracking in the shell

The `list_documents_awaiting_parsing` tool helps you track queue depth and automates your cron jobs directly through the command line. You can spot processing pile-ups before they affect downstream databases. The agent can search for specific files using `search_parsed_documents` to verify if a re-uploaded document has finished processing. It then grabs the completed dataset with `list_parsed_documents` to feed your database import scripts.

Setup guide

Set up Docparser 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 docparser-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http docparser-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 Docparser 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": {
    "docparser-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 Docparser. 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 Docparser 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 Docparser MCP in Claude Code

Run the command `claude mcp add --transport http docparser-mcp -- ` in your terminal. This registers the server and makes all ten document parsing tools available in your CLI session.

Yes. You can ask Claude Code to check your queue. The agent runs `list_documents_awaiting_parsing` and displays the pending files directly in your terminal.

The agent calls `list_failed_document_extractions` to find broken runs. The agent uses the MCP tool definitions to call the API and pull the layout details using `get_parser_details` to show you exactly why the rules failed to match.

Yes, you can ask the agent to fetch results. Claude Code calls `get_document_extraction_results` and saves the raw data directly to a local file in your preferred format.

Your API metadata and parsed document texts are handled in a secure, isolated V8 sandbox using the MCP protocol. All requests go directly to the Docparser API, ensuring your authentication tokens never touch persistent storage.

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