# Suidasu Muse connector

From musedirectory.ai, the independent directory of Meta Muse connectors. Not affiliated with Meta.

## Suidasu

Turn scanned invoices, faxes and handwritten notes into structured data Muse can use.

- Record: https://musedirectory.ai/connector/suidasu
- Category: Productivity
- Developer: Suidasu (https://www.suidasu.com/mcp)
- Muse status: Extra setup. Not in Muse's Connectors list yet. Muse can still use it: its page gives you a request to paste into Muse.
- Health: Working, 359ms, checked 2026-11-20T16:15:44Z
- Endpoint: https://api.suidasu.com/mcp
- Auth: Needs an access key; Pricing: unknown
- Screening: Screened, no issues found (2026-11-18T17:56:20Z)
- Source: Found in the official MCP Registry (com.suidasu/suidasu) https://registry.modelcontextprotocol.io/v0/servers?search=com.suidasu%2Fsuidasu

Connects Muse to Suidasu's AI-OCR service, which reads invoices, faxes, handwriting and photos and extracts the fields you define with custom layouts. Muse can pull that structured data out of documents and put it to work in your records or workflows.

Example request: "Read the stack of supplier invoices I scanned and pull out the vendor, date and total for each one."

How to connect: Not in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use Suidasu to help me. It is a free service with an MCP server at https://api.suidasu.com/mcp. It needs an API key from Suidasu; ask me to enter it through your secure credential prompt. Ask me before you share anything with it." Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.

Tools:
- extract_data: Extract structured data from an image using a predefined layout. Uses AI cascade strategy for optimal cost-accuracy balance.
- list_layouts: List all available extraction layouts with their field definitions
- get_extraction: Get the result of a previous extraction by ID. Returns extracted data, a signed URL for downloading the original image (valid for 1 hour), and error_message if the extraction failed (e.g. inappropriate_content, prohibited_content, low_confidence).
- list_extractions: List OCR extractions filtered by project and date range. Failed extractions include error_message field indicating the failure reason (e.g. scan.error.inappropriate_content, scan.error.low_confidence).
- list_projects: List all projects with their layouts and field definitions
- update_extraction: Update the extracted data of an extraction result
- delete_extraction: Delete an extraction result. A parent (root) ID deletes the whole upload (parent and all records); a record ID deletes only that record and renumbers the rest. Deleting an extraction that superseded an older extraction of the same file makes the older one current again.
- create_project: Create a new project with layout options
- update_project: Update an existing project
- delete_project: Delete a project (soft delete)
- create_layout: Create a new layout with field definitions. The created layout can be assigned to a project via create_project.
- update_layout: Update an existing layout (replaces all fields)
- delete_layout: Delete a layout (soft delete)
- generate_recipe: Analyze a sample file and generate layout proposals. Accepts images, PDF, CSV, Excel (xlsx), Markdown, and plain text (e.g. a layout specification document). AI automatically detects the document type and suggests appropriate field definitions. Requires Standard plan or higher. D
- create_layout_from_recipe: Create a new layout from a recipe proposal. Use the output from generate_recipe to create a layout.
- export_extractions: Export extraction data to CSV or Excel format. Returns base64-encoded file data.
- list_templates: List all available system templates (business_card, invoice, receipt, etc.) with their field definitions
- import_template: Import a system template as a new layout for your account
- get_usage_stats: Get current month's usage statistics including extraction count, remaining free extractions, and success rate
- get_billing_info: Get billing information for a specific month including invoice amount and billable extraction count from Stripe
- check_fields: Validate field definitions for AI extractability. Returns confidence score and improvement suggestions.

Screening checks:
- MCP handshake: pass (Answered in 265ms)
- Domain against threat feeds (Cloudflare security DNS): pass (api.suidasu.com, www.suidasu.com not flagged)
- Published packages against the OSV malicious-package database: n/a (No npm or PyPI package published)
- Hidden instructions or invisible characters in tool text: pass (21 tools read, nothing found)
- Inputs asking for passwords, card numbers or seed phrases: pass (None found)
- Domain and redirects: pass (Domain registered 336 days ago)
- AI review of purpose and tool behavior: pass (No concerns)
