How to Use the Unstructured MCP in Windsurf

Q: Can I check history when using Unstructured with Windsurf?

Yep. You use listworkflowjobs to see both active jobs and historical records of workflow runs. This is key for debugging why a transformation failed or confirming successful completion.

Q: Does the MCP Server support multiple data sources in Windsurf?

Absolutely. You use listdatasources to see every configured connector, meaning you can feed the processing workflow from S3, GCS, or whatever other remote location you've set up.

Set a goal, and let Windsurf figure out all the steps using Unstructured’s processing tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Unstructured MCP to Windsurf

Create your Vinkius account to connect Unstructured to Windsurf 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 Unstructured with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Unstructured MCP Server: Manage entire data pipelines.

You tell Cascade to process some messy documents. It starts by listing available remote connections with `list_data_sources`, confirming where the raw files live. Then, it checks the job status using `list_workflow_jobs` before triggering the actual run with `trigger_workflow_execution`. This lets you set a complex goal and watch Cascade handle every single step.

Inspect workflow configuration details.

Need to know what's supposed to happen? Use `get_workflow_details` to pull the exact settings for any defined processing pipeline. This gives you visibility into the full scope of data transformation. It also lets you review all existing end-to-end document pipelines by calling `list_processing_workflows`, keeping your entire system mapped out.

Understand where processed data lands.

The agent can map out all possible destinations for the finished product. Use `list_data_destinations` to see every configured target, whether it's a vector database or some SQL backend. If you want to know what sources are available—S3, GCS, etc.—you just run `list_data_sources`. This gives full context before any data moves.

Setup guide

Set up Unstructured MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Unstructured 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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Unstructured payment history." If connected, Cascade will call the Unstructured tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "unstructured-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 Unstructured. 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 Unstructured 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 Unstructured MCP in Windsurf

Windsurf's Cascade agent handles the whole lifecycle. You just set the goal: 'Process these documents.' The MCP Server then autonomously reads sources, triggers the workflow using `trigger_workflow_execution`, and manages job status, all without you having to prompt every step.

This server handles raw input files from various remote connectors (like S3 or GCS) and transforms them into structured formats ready for storage in destinations like Vector DBs and SQL databases.

Yep. You use `list_workflow_jobs` to see both active jobs and historical records of workflow runs. This is key for debugging why a transformation failed or confirming successful completion.

Absolutely. You use `list_data_sources` to see every configured connector, meaning you can feed the processing workflow from S3, GCS, or whatever other remote location you've set up.

The server touches raw input files and configuration metadata. Since it manages sources and destinations, all connections and processing details are exposed to your AI client's context.

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