Suparse Document Processing
Connects Claude to the Suparse Document Processing API for extracting structured data from PDFs and documents into JSON, CSV, XLSX, or Google Sheets. You get six tools: extract_file and extract_folder for processing documents with auto-detection or team templates, list_templates to browse available schemas, fetch_json_results for inline JSON, download_results to write exports directly to disk, and delete_documents for cleanup. The server reads local files and writes output wherever it has permissions, so only connect it to trusted clients. Requires a Suparse API key set via environment variable or config file. Useful when you need to programmatically pull tables, forms, or receipts out of documents and into structured formats.
- tools
- 17
- auth
- Secret needed
- transport
- STDIO
- env var
- 1
- last updated
- Oct 19, 2026
Tools
17 toolsPublic tool metadata for what this MCP can expose to an agent.
extract_fileCombined upload and processing. defer is the default and returns task/document IDs after polling; return_json returns exported groups with per-input task status and document IDs.
Combined upload and processing. defer is the default and returns task/document IDs after polling; return_json returns exported groups with per-input task status and document IDs.
No parameter schema in public metadata yet.
extract_folderCombined upload and processing for a folder of documents.
Combined upload and processing for a folder of documents.
No parameter schema in public metadata yet.
start_file_extractionUpload and return task IDs immediately, without polling or exporting.
Upload and return task IDs immediately, without polling or exporting.
No parameter schema in public metadata yet.
start_folder_extractionUpload a folder's documents and return task IDs immediately, without polling or exporting.
Upload a folder's documents and return task IDs immediately, without polling or exporting.
No parameter schema in public metadata yet.
wait_for_task_extractionPoll a remote task until processing completes.
Poll a remote task until processing completes.
No parameter schema in public metadata yet.
get_task_resultsRead one bounded page of partial task documents.
Read one bounded page of partial task documents.
No parameter schema in public metadata yet.
list_templatesList summary or full template records, grouped into team_templates and system_templates.
List summary or full template records, grouped into team_templates and system_templates.
No parameter schema in public metadata yet.
start_quick_schema_creationStart automatic schema creation.
Start automatic schema creation.
No parameter schema in public metadata yet.
get_quick_schema_creationInspect an automatic schema creation run.
Inspect an automatic schema creation run.
No parameter schema in public metadata yet.
wait_for_quick_schema_creationWait for an automatic schema creation run to finish.
Wait for an automatic schema creation run to finish.
No parameter schema in public metadata yet.
fetch_json_resultsReturn validated JSON export results by document ID.
Return validated JSON export results by document ID.
No parameter schema in public metadata yet.
fetch_document_resultFetch one document's structured JSON result.
Fetch one document's structured JSON result.
No parameter schema in public metadata yet.
download_resultsExport documents and save the response to a local path in JSON, CSV, XLSX, or Google Sheets format.
Export documents and save the response to a local path in JSON, CSV, XLSX, or Google Sheets format.
No parameter schema in public metadata yet.
get_export_jobInspect a known remote export job.
Inspect a known remote export job.
No parameter schema in public metadata yet.
wait_for_export_jobWait for a known remote export job to complete.
Wait for a known remote export job to complete.
No parameter schema in public metadata yet.
download_export_jobDownload a completed export job after reconnecting, preserving original bytes.
Download a completed export job after reconnecting, preserving original bytes.
No parameter schema in public metadata yet.
delete_documentsDelete remote documents by ID.
Delete remote documents by ID.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
SUPARSE_API_KEY*secretSuparse API key used to authenticate requests.
Readme
Suparse MCP Server
MCP stdio server for the Suparse Document Processing API. Use it from local MCP clients such as Claude Code and Codex to extract structured data from documents into JSON, CSV, XLSX, or Google Sheets; process single files or folders, including encrypted PDFs; let Suparse auto-detect extraction schemas or apply your team templates; create schemas automatically; split mixed multi-page documents; and download or clean up results by document ID.
Security Boundary
This is a local stdio MCP server. Connected MCP clients can ask it to read local document paths and write export files wherever the server process has permission. Only connect it to MCP clients and workspaces you trust.
Requirements
- A Suparse API key
- Node.js 20+
Authentication
The MCP server reads credentials from:
SUPARSE_API_KEY~/.config/suparse/config.json
Prefer passing SUPARSE_API_KEY through your client's environment or secret-input support. The fallback file is implemented by Suparse and contains { "apiKey": "your_api_key" }. Protect it as a credential file.
Details
- Repository
- github.com/suparse/suparse-mcp
- Website
- www.suparse.com
- Categories
- Search & Web Crawling, Data & Analytics
- Package
@suparse/mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
Related Search & Web Crawling MCP servers
View all
Slipstreamtathagat22/slipstreamShared distillation cache for AI agents — every fetch ~73-89% fewer tokens via a shared cache.0stars
Apollo Intelligencebnmbnmai/mcp-proxy36 tools: intel feeds, DeFi, crypto, OSINT, NLP, scraping, proxy. x402 micropayments.0stars
Superjob Mcptheyahia/superjob-mcpMCP server for SuperJob.ru API — vacancy search, employers. Requires API key.0starsVk Mcptheyahia/vk-mcpMCP server for VK API — wall posts, news search, users, groups. 4 tools.0stars
Skillsindexthomasblc/skillsindex-mcpSearch and score 11,000+ AI agent tools: MCP servers, Claude skills, GPT actions, IDE plugins.0stars
Voidfeed Mcpvoidfeedai-ops/voidfeed-mcpKnowledge API for AI agents — content, agent directory, model benchmarks, semantic search.0stars