Earshot is a toolkit that lets AI coding agents analyse and describe audio, check how well sound fits a description or a video, and create their own sound effects in code. It runs locally on a CPU as a command-line tool, a Python library or an MCP server.
arvx-mcp
by centricai
A connector that lets MCP-compatible AI assistants run ARVX Readings, which assess the health of the email relationship between two people. It is meant for people building CRM or email tools, or agents that need to judge how a business relationship is going.
Proof level: ReadNew and promisingApache-2.0
No demo yet
Proof level: Read. We read its README and licence and ran our automatic checks. We have not run it yet. So this page is based on its README and our automatic checks.
The catch
Check this first: Depends on the paid ARVX hosted service: the first 3 Readings are free, then 43p-equivalent (43 cents) each, prepaid.
Things to check
- Depends on the paid ARVX hosted service: the first 3 Readings are free, then 43p-equivalent (43 cents) each, prepaid
- Needs a personal ARVX key, with a photo ID and selfie check via Stripe before the first payment
- Email content goes to a third-party service, so check the terms and privacy implications
- The repository is new with no stars
Can you use arvx-mcp commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Did it work for you?
One answer per person for each tool a day, with no account and no cookies. Your answer is remembered in this browser only. How we count
What can you do with arvx-mcp?
- Run a Reading on two people from the emails between them and get colour-coded results for areas such as clarity and responsiveness
- Get up to three predictions about what happens next, each with a suggested action
- Compare a new Reading with the last one on the same pair to see what has changed
How do you get arvx-mcp running?
Sign up at ARVX to create a key, then add the remote MCP server URL (https://mcp.arvx.ai/mcp) to your client's settings with the key in a header.
Follow the official instructions in the project README.
Add it to Claude Code
claude mcp add --transport http arvx https://mcp.arvx.ai/mcp
This one runs on the maker's server, not your computer, so what you send it leaves your machine.
From the official MCP Registry (ai.arvx/arvx). Only connect MCP servers you trust: they can act on your behalf.
Make money with it
A freelancer could offer client-relationship check-ups to small businesses, using Readings to flag accounts at risk.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Spot client or customer relationships that are drifting, such as slow replies, so you can follow up before losing the account
- Add relationship-health insights to a CRM or email product you are building
Checked 11 Nov 2026. Summary drafted by AI from the project's README. Proof level 1 of 4, Read: we read its readme and licence and ran our automatic checks. we have not run it yet.
Similar tools in MCP servers
Kanzo is a small kanban board that runs in your browser and also works as an MCP server, so you and your AI coding agents share the same task list. All data sits in one local folder, which can be synced between machines through a private git repository.
A collection of 77 unofficial MCP servers that let AI assistants search and read Iranian websites such as Digikala, Torob, Divar, Snappfood and Alibaba. It is for comparing prices in Toman, finding jobs, cars, travel, laws and market data from Claude, Cursor or any MCP client.