# Mervext Muse connector

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

## Mervext

Extract invoices, receipts and contracts into structured data with confidence scores

- Record: https://musedirectory.ai/connector/mervext
- Category: Finance & Bills
- Developer: V Studio Digital (https://mervext.com)
- 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, sign-in needed, 313ms, checked 2026-10-29T11:46:01Z
- Endpoint: https://mcp.vstudiodigital.com/mcp
- Auth: Needs an access key; Pricing: unknown
- Screening: Screened, no issues found (2026-10-29T01:26:34Z)
- Source: Found in the official MCP Registry (com.vstudiodigital/mervext) https://registry.modelcontextprotocol.io/v0/servers?search=com.vstudiodigital%2Fmervext

Mervext extracts key information from invoices, receipts and contracts into structured JSON format. EU-hosted service that provides per-field confidence scores to help validate extracted data accuracy.

Example request: "Extract line items and totals from a receipt and add them to my expense tracker"

How to connect: Not in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use Mervext to help me. It is a free service with an MCP server at https://mcp.vstudiodigital.com/mcp. It needs an API key from V Studio Digital; 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.

Screening checks:
- MCP handshake: pass (Requires sign-in)
- Domain against threat feeds (Cloudflare security DNS): pass (mcp.vstudiodigital.com, mervext.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: n/a (Tools are behind sign-in)
- Inputs asking for passwords, card numbers or seed phrases: n/a (Tools are behind sign-in)
- Domain and redirects: pass (Domain registered 64 days ago)
- AI review of purpose and tool behavior: pass (No concerns)