DocRouter MCP Server

Model Context Protocol server for seamless AI assistant integration

View on GitHub

Overview

The DocRouter MCP Server enables AI agents to interact directly with DocRouter.AI for document processing workflows.

• Document management and retrieval
• AI-powered document processing
• Schema and prompt configuration
• Web forms configuration

Installation

Prerequisites

• Node.js 18+ installed on your system

Installation

npm install -g @docrouter/mcp

Verify installation:

which docrouter-mcp
docrouter-mcp --help

Configuration

Configure the MCP server for your AI assistant:

• Cursor IDE: Create .mcp.json
• Claude Desktop: Update claude_desktop_config.json
• Claude Agent: Configure MCP server

{
  "mcpServers": {
    "docrouter": {
      "command": "docrouter-mcp",
      "env": {
        "DOCROUTER_API_URL": "https://app.docrouter.ai/fastapi",
        "DOCROUTER_ORG_ID": "your-org-id",
        "DOCROUTER_ORG_API_TOKEN": "your-api-token"
      }
    }
  }
}

Replace your-org-id and your-api-token with your actual DocRouter credentials.

Example Prompts

Create a Schema

Create a schema for extracting invoices with these fields:
- invoice_number (string, required)
- date (string, format: date)
- total_amount (number, required)
- vendor_name (string)
- line_items (array of objects). The line_items object: 
  - description 
  - quantity 
  - unit_price
  - total

Update a Schema

Update the invoice schema to add a new optional field:
- payment_terms (string)

Create a Prompt

Create a prompt for extracting invoice data from documents.

Configure it with the invoice schema, and tag it with a tag named 'green'

Update a Prompt

Update the invoice extraction prompt to ensure the date is in YYYY-MM-DD format."

Available Tools

Click on any tool name to see detailed information about its parameters and usage.

Documents

upload_documents(documents)	Upload documents
list_documents(skip, limit, tagIds, nameSearch, metadataSearch)	List documents
get_document(documentId, fileType)	Get document by ID
update_document(documentId, documentName, tagIds, metadata)	Update document metadata
delete_document(documentId)	Delete document

OCR

get_ocr_blocks(documentId)	Get OCR blocks
get_ocr_text(documentId, pageNum)	Get OCR text
get_ocr_metadata(documentId)	Get OCR metadata

LLM Extraction

run_llm(documentId, promptRevId, force)	Run AI extraction
get_llm_result(documentId, promptRevId, fallback)	Get extraction results
update_llm_result(documentId, promptId, result, isVerified)	Update extraction results
delete_llm_result(documentId, promptId)	Delete extraction results

Tags

create_tag(tag)	Create tag
list_tags(skip, limit, nameSearch)	List tags
get_tag(tagId)	Get tag by ID
update_tag(tagId, tag)	Update tag
delete_tag(tagId)	Delete tag

Prompts

create_prompt(prompt)	Create prompt
list_prompts(skip, limit, document_id, tag_ids, nameSearch)	List prompts
get_prompt(promptRevId)	Get prompt by ID
update_prompt(promptId, content)	Update prompt
delete_prompt(promptId)	Delete prompt

Schemas

create_schema(name, response_format)	Create schema
list_schemas(skip, limit, nameSearch)	List schemas
get_schema(schemaRevId)	Get schema by ID
update_schema(schemaId, schema)	Update schema
delete_schema(schemaId)	Delete schema
validate_schema(schema)	Validate schema format
validate_against_schema(schemaRevId, data)	Validate data against schema

Forms

create_form(name, response_format)	Create form
list_forms(skip, limit, tag_ids)	List forms
get_form(formRevId)	Get form by ID
update_form(formId, form)	Update form
delete_form(formId)	Delete form
submit_form(documentId, formRevId, submission_data, submitted_by)	Submit form
get_form_submission(documentId, formRevId)	Get form submission
delete_form_submission(documentId, formRevId)	Delete form submission
validate_form(form)	Validate form format

LLM Chat

run_llm_chat(messages, model, temperature, max_tokens, stream)

Run LLM chat

Help

help()	Get general API help
help_prompts()	Get prompts help
help_schemas()	Get schemas help
help_forms()	Get forms help

View on GitHub Get API Credentials

</main> </div>

Description

Parameters

Required Parameters