Skip to main content
Reducto is a document processing API that converts complex documents — PDFs, scanned files, and more — into structured, machine-readable content. The Reducto MCP server lets you parse documents, extract structured data, split documents into sections, and fill forms using natural language.

​
What Can It Do?

  • Parse documents — convert PDFs and other files into structured text, tables, and figures
  • Extract structured data — pull specific fields from documents using a JSON schema
  • Split documents — divide a document into logical sections based on descriptions
  • Edit documents — fill forms or modify documents with natural language instructions
  • Manage jobs — track, monitor, and cancel document processing jobs

​
Where to Use It

Add Reducto as a tool to any agent. The agent can then process and extract data from 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 Reducto API key
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 Reducto 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., “Extract invoice data from a PDF”)
  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
Upload DocumentUpload a file from Gumloop storage to Reducto for processing
Download DocumentDownload a Reducto result file back to Gumloop storage
Parse DocumentParse a document into structured content including text, tables, and figures
Extract DataExtract structured data from a document using a JSON schema
Split DocumentSplit a document into logical sections based on descriptions
Edit DocumentFill forms or modify a document with natural language instructions
List JobsList processing jobs with pagination support
Get Job StatusGet the status and result of a processing job
Cancel JobCancel a running processing job

​
Example Prompts

Use these with your agent or in the Agent Node: Parse a document: 
Upload and parse the contract PDF, then give me a summary of the key terms
Extract structured data: 
Extract the invoice number, date, line items, and total from this PDF invoice
Split a document: 
Split this 50-page report into sections: Executive Summary, Methodology, Results, and Appendix
Fill a form: 
Fill in the application form with the applicant's name, address, and date of birth from the provided data
Check job status: 
What's the status of my document processing jobs?

​
Troubleshooting

IssueSolution
Upload failingEnsure the file exists in Gumloop storage before uploading
Extraction missing fieldsRefine your JSON schema to be more specific about the fields you need
Job taking too longUse Get Job Status to monitor progress; large documents may take longer
Tool not availableVerify the tool is enabled in your agent’s MCP configuration
For best extraction results, provide a detailed JSON schema that describes exactly what fields you need and their expected data types. The more specific your schema, the more accurate the extraction.

​
Need Help?

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