Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.gumloop.com/llms.txt

Use this file to discover all available pages before exploring further.

Extend is a document processing platform that turns PDFs, images, and scans into structured data. The Extend MCP server lets you run processors, parse files, and manage document workflows using natural language.

​
What Can It Do?

  • Run document workflows with files or text inputs
  • Parse files into clean, chunked content for processing
  • Extract and classify data from documents with processors
  • Monitor runs with filtering and lifecycle management

​
Where to Use It

Add Extend as a tool to any agent. The agent can then process documents conversationally, choosing the right actions based on context. To add an MCP tool to your agent:
  1. Open your agent’s configuration
  2. Click Add tools → Connect an app with MCP
  3. Search for the integration and select it
  4. Authenticate with your account
You can control which tools your agent has access to. After adding an integration, click on it to enable or disable specific tools based on what your agent needs.

​
In Workflows (Via Agent Node)

For automated pipelines, use an Agent Node with Extend tools. This gives you the flexibility of an agent within a deterministic workflow.

​
As a Custom MCP Node

You can also create a standalone MCP node for a specific action. This generates a reusable node that performs one task, useful when you need the same operation repeatedly in workflows.
To create a custom MCP node:
  1. Go to your node library and search for the integration
  2. Click Create a node with AI
  3. Describe the specific action you want (e.g., “Parse this PDF to markdown”)
  4. Test the node and save it for reuse
Custom MCP nodes are single-purpose by design. For tasks that require multiple steps or dynamic decision-making, use an agent instead.

​
Available Tools

ToolDescription
List Workflow RunsList runs with filtering by status
Get Workflow RunGet details of a specific run
Run WorkflowRun a workflow with files or text
Run ProcessorRun extraction or classification
List Processor RunsList processor runs with filtering
Get Processor RunGet details of a processor run
Cancel/Delete Processor RunManage processor runs
Parse FileParse files to markdown or spatial format
Get Parser RunGet parser run status and results

​
Example Prompts

Use these with your agent or in the Agent Node: Run a workflow: 
Run the invoice processing workflow on this PDF
Parse a document: 
Parse this PDF to markdown and return the text chunks
Extract data: 
Run the contract extraction processor on this document
Check run status: 
Get the status of my latest workflow runs

​
Troubleshooting

IssueSolution
Agent not finding the right dataUse specific workflow or processor names
Action not completingCheck that you’ve authenticated and the file URL is accessible
Unexpected resultsThe agent may chain multiple tools (e.g., parsing first, then extracting). Review the agent’s reasoning to understand its approach.
Tool not availableVerify the tool is enabled in your agent’s MCP configuration
Agents are smart enough to chain multiple API calls together. For example, asking “Extract invoice details from this PDF” will parse the file first, then run the extractor. If results seem off, check the agent’s step-by-step reasoning.

​
Need Help?

Use this integration directly in Claude or Cursor. Connect remotely via the Extend MCP server using your Gumloop credentials.