# Patchwell Muse connector

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

## Patchwell

Research with sources, transcribe audio with timestamps, and clean up spreadsheets with a change log.

- Record: https://musedirectory.ai/connector/patchwell
- Category: Productivity
- Developer: Patchwell (https://patchwell.io)
- 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, 693ms, checked 2026-11-07T00:01:18Z
- Endpoint: https://patchwell.io/mcp/
- Auth: Needs an access key; Pricing: unknown
- Screening: Screened, no issues found (2026-11-07T01:06:13Z)
- Source: Found in the official MCP Registry (io.patchwell/patchwell) https://registry.modelcontextprotocol.io/v0/servers?search=io.patchwell%2Fpatchwell

Connects Muse to cited web research, audio transcription with word-level timestamps, and CSV or Excel cleanup that records every change. Muse can gather sourced answers, turn recordings into timestamped text, and tidy messy spreadsheets while keeping a log of what was edited.

Example request: "Transcribe this interview with timestamps and clean up the expense spreadsheet I downloaded, keeping a log of what you changed."

How to connect: Not in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use Patchwell to help me. It is a free service with an MCP server at https://patchwell.io/mcp/. It needs an API key from Patchwell; 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 (patchwell.io 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 (No redirects off the domain)
- AI review of purpose and tool behavior: pass (No concerns)