How to Use the Affinda MCP in VS Code Copilot

Q: How do I share the Affinda MCP setup in VS Code Copilot?

Create a .vscode/mcp.json file in your repository root. Commit this file to version control. Every developer on your team gets the exact same tools automatically.

Equip your entire engineering team with Affinda parsing inside VS Code Copilot.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Affinda MCP to VS Code Copilot

Create your Vinkius account to connect Affinda to VS Code Copilot 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 Affinda with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate document extraction in VS Code

Affinda turns unstructured PDFs into clean JSON straight from your editor via MCP. Copilot triggers `create_document` with a public URL to start parsing a test file. The AI client handles the network request while you focus on writing the application logic. Retrieving that data takes one step. Copilot runs `get_document` to fetch the parsed results. You ask the agent to map the extracted fields to your database schema, and it writes the exact SQL queries needed.

Discover supported Affinda models

Knowing what your account can parse saves development time. Copilot executes `list_document_types` to list every available model. You ask if the API supports receipts, and the agent checks the live configuration immediately. Workspace management works the same way. The `list_workspaces` MCP tool pulls your container IDs so Copilot can use them in your code. The agent hardcodes the correct environment variables based on real account data.

Monitor batches via this MCP Server

Keeping track of test uploads usually requires switching to a browser. Copilot calls `list_documents` to pull the status of your recent API calls. The agent tells you exactly which files succeeded and which ones are stuck in pending. This keeps your workflow entirely inside the editor. You spot integration issues early because the AI client reads the raw API responses. Fixing a bad upload script takes minutes instead of hours.

Setup guide

Set up Affinda MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Affinda MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Affinda tools listed. Try asking: "List my recent Affinda transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "affinda-mcp": {
      "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 Affinda. 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 Affinda 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 Affinda MCP in VS Code Copilot

Create a `.vscode/mcp.json` file in your repository root. Commit this file to version control. Every developer on your team gets the exact same tools automatically.

You need to provide a public URL. The current tools do not support local file uploads directly from your machine. Host the test files on a public server first.

Agent mode allows the AI to call the API on your behalf. It executes the tools, reads the JSON responses, and uses that context to write better code.

The entire MCP integration requires this version or higher. Older versions lack the underlying protocol support to connect external servers. Update your editor before configuring the JSON file.

Identity documents and personal identification numbers stay strictly within your managed session. Vinkius drops the container the second the operation completes. No persistent storage means zero risk of data exposure.

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