docuprox-mcp
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@docuprox-mcp Process the invoice at documents/invoice.pdf using template default."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
docuprox-mcp
MCP (Model Context Protocol) server for the DocuProx document-processing API. Exposes DocuProx as tools that any MCP-compatible AI client can call — Claude Desktop, Claude Code, Cursor, Windsurf, and more.
Quickstart (npx — no install required)
DOCUPROX_API_KEY=your_key DOCUPROX_BASE_URL=https://api.docuprox.com/v1 npx docuprox-mcpRequires Node.js ≥ 18.
Related MCP server: MCP Server for CAP
Configuration
Variable | Required | Description |
| yes | Your DocuProx API key |
| yes | Base URL of the DocuProx API (e.g. |
Connect to an MCP Client
Claude Desktop
macOS — ~/Library/Application Support/Claude/claude_desktop_config.json
Windows — %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"docuprox": {
"command": "npx",
"args": ["docuprox-mcp"],
"env": {
"DOCUPROX_API_KEY": "your_api_key_here",
"DOCUPROX_BASE_URL": "https://api.docuprox.com/v1"
}
}
}
}Claude Code (CLI)
claude mcp add docuprox -e DOCUPROX_API_KEY=your_api_key_here -e DOCUPROX_BASE_URL=https://api.docuprox.com/v1 -- npx docuprox-mcpCursor / Windsurf
Add to your MCP settings (.cursor/mcp.json or equivalent):
{
"mcpServers": {
"docuprox": {
"command": "npx",
"args": ["docuprox-mcp"],
"env": {
"DOCUPROX_API_KEY": "your_api_key_here",
"DOCUPROX_BASE_URL": "https://api.docuprox.com/v1"
}
}
}
}Available Tools
process_job
Submit a document for asynchronous processing. Returns a job_id to track with poll_job or job_results.
Argument | Type | Required | Description |
| string | yes | Path to file on disk (jpg, png, pdf, zip) |
| string | no | UUID of a DocuProx template |
| string | no* | Document category — required when no |
| object | no | Custom extraction schema |
| string | no | Free-text guidance for the AI |
| object | no | Key-value overrides for STATIC template placeholders |
Example: "Submit the invoice at
/tmp/invoice.pdfusing template123e4567-e89b-12d3-a456-426614174000"
process_agent
Submit a document for synchronous extraction. Blocks until done and returns results directly — no polling needed. Credits are automatically refunded on failure.
Argument | Type | Required | Description |
| string | yes | Path to file on disk |
| object | yes | Extraction schema |
| string | yes | Document category |
| string | no | Free-text guidance |
| object | no | Key-value STATIC overrides |
Example: "Extract passport data from
/home/user/passport.jpg. Use document_type='passport' and prompt_json{ 'name': 'full name', 'dob': 'date of birth' }"
job_status
Check the status of an async job.
Argument | Type | Required | Description |
| string | yes | UUID from |
Returns: { job_id, status } where status is one of:
NEW → UNZIP FILE → UNZIP FILE SUCCESS / UNZIP FILE FAILED → PROCESS IMAGE → PROCESS IMAGE SUCCESS / PROCESS IMAGE FAILED → SUCCESS / FAILED
poll_job
Block until a job finishes (or times out). Retries job_status internally on a timer.
Argument | Type | Required | Default | Description |
| string | yes | — | UUID from |
| number | no |
| Poll interval in ms |
| number | no |
| Max wait in ms (5 min) |
Example: "Submit
/tmp/batch.zipthen wait for the result" — Claude will callprocess_jobthenpoll_jobautomatically.
job_results
Fetch the extracted results of a completed async job.
Argument | Type | Required | Default | Description |
| string | yes | — | UUID from |
| string | no |
| Output format: |
Example: "Get the results for job
0869d5ec-5cfe-4960-878d-8b4ec1900726in CSV format"
How File Uploads Work
Every tool that accepts a file_path:
Resolves it to an absolute path
Reads the file into a
BufferDetects MIME type from the file extension
Sends it as
multipart/form-datawith field nameactual_image
The AI never sees or handles base64 — just pass a local file path.
Error Handling
Error | Cause |
File not found |
|
API error | HTTP status + response body surfaced in the tool result |
Invalid arguments | Zod validation fires before any API call |
Credit failure | 402/403 from |
Local Development
# Clone and install
git clone <repo>
cd docuprox-mcp
npm install
# Run in dev mode (no build step)
DOCUPROX_API_KEY=test DOCUPROX_BASE_URL=http://localhost:5000/v1 npm run dev
# Build
npm run build
# Inspect with MCP Inspector
npx @modelcontextprotocol/inspector node dist/index.jsProject Structure
docuprox-mcp/
├── index.ts ← MCP server entry point (stdio transport)
├── config.ts ← Env-var config loader
├── client.ts ← Axios API client (multipart/form-data uploads)
├── tools.ts ← Zod schemas + MCP tool definitions
├── handlers.ts ← Maps tool names → client calls
├── package.json
└── tsconfig.jsonLicense
MIT
Available Tools
5 toolsjob_resultsA
Fetch the extracted results of a completed asynchronous DocuProx processing job. Requires a valid job_id and optionally a format ('json' or 'csv').
Inputs: job_id (required), result_format.
job_statusB
Check the current status of an asynchronous DocuProx processing job. Returns the job_id and status string (e.g. NEW, UNZIP FILE, UNZIP FILE SUCCESS, UNZIP FILE FAILED,PROCESS IMAGE, PROCESS IMAGE SUCCESS,PROCESS IMAGE FAILED,SUCCESS,FAILED).
Inputs: job_id (required).
poll_jobA
Poll an asynchronous DocuProx job until it reaches a terminal status (COMPLETED, FAILED, or ERROR) or a timeout is reached. Useful to block until a job is done without manual retries.
Inputs: job_id (required), timeout_ms, interval_ms.
process_agentA
Submit a document for SYNCHRONOUS agentic extraction via DocuProx. Reads the file from disk, uploads as multipart/form-data, and waits for the result. Returns the extracted data directly (no job polling needed). Credits are deducted and refunded on failure.
Inputs: file_path (required), prompt_json (required), document_type (required), static_values, +1 more.
process_jobA
Submit a document (image, PDF, or zip) for asynchronous processing via DocuProx. Reads the file from disk and uploads it as multipart/form-data. Returns a job_id you can track with job_status or poll_job.
Inputs: file_path (required), prompt_json, template_id, document_type, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
The tools are mostly distinct: process_job and process_agent both submit documents but differ clearly by async vs sync behavior, and job_status vs poll_job are differentiated as one-time check vs blocking wait. Minor ambiguity exists between job_status and poll_job since both relate to job progress, but the descriptions adequately clarify their purposes.
Names are readable and use snake_case, but the pattern is mixed: process_job, process_agent, and poll_job are verb_noun, while job_status and job_results are noun_noun. This inconsistency is noticeable but not chaotic, and each name still conveys its intended function reasonably well.
With 5 tools, the server is well-scoped for its purpose: async submission, status checking, polling, result retrieval, and sync submission. Each tool serves a discrete workflow step without unnecessary redundancy.
The toolkit covers both asynchronous and synchronous processing flows end-to-end: submit, track, wait, and retrieve results. There are no obvious dead ends for the core document-processing use case, and the missing ability to cancel or delete jobs is not essential to the stated purpose.
Maintenance
Related MCP Connectors
Hosted document tools for agents: extract, parse, classify, convert, OCR, sign, and redact.
Pay-per-call document and web tools for AI agents: PDF parsing and OCR (Japanese-strong), web and structured extraction, invoice verification, company profiles and PDF utilities. x402 (USDC on Base), no API key; failed calls are never charged.
Human-in-the-loop document extraction: submit a doc, get validated fields and an audit trail.
DocForge turns documents into structured data. Upload a PDF, image, or Office file and get fielded JSON back with per-field confidence scores. 95 templates (invoices, receipts, bank statements, ID docs), custom JSON Schema mode, auto-detect, natural-language instructions. Keyless demo tool included. Free 7-day trial.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI assistants to parse and convert PDFs and images to structured text formats using the Doc2x v2 API. Supports asynchronous document processing, format conversion, and file downloads with configurable polling and timeout settings.1448 npm3MIT
- AlicenseNot gradedqualityDmaintenanceEnables Claude to interact with a document processing backend, providing tools for listing, retrieving, uploading, and processing documents, as well as resources for pending documents and statistics.ISC
- AlicenseBqualityBmaintenance41 finished-job AI tools on one credit wallet: documents to schema-valid JSON, field extraction, PII redaction, contract review, triage, research, moderation, agent memory. Failed calls never burn credits.4154 npm1MIT
- AlicenseNot gradedqualityCmaintenanceEnables MCP-compatible agents to convert PDFs and images into Markdown, JSON, HTML, LaTeX, DOCX, or ZIP by wrapping a document parsing service's REST API as callable tools, including uploads, parsing jobs, progress polling, and result downloads.1Apache 2.0