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.
mcp
by elfa-ai
An MCP server that connects AI assistants to the Elfa API, giving them market events, social mentions, trending tokens and account rankings across crypto and equities. It also lets the assistant build and manage Auto queries that watch the market and fire an action when set conditions are met.
Proof level: ReadWorth a lookMIT
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: Needs an Elfa API key, and calls use paid credits.
Things to check
- Needs an Elfa API key, and calls use paid credits
- Language-model-backed endpoints are charged per attempt and can exceed client timeouts
- Auto queries run unattended and can fire actions, so check them carefully before activating
- Focused on crypto and market data, which carries financial risk if used for trading decisions
- Depends on a third-party hosted API
Can you use 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 mcp?
- Ask your AI assistant what is trending in crypto and which social posts are driving attention
- Turn a plain-language monitoring request into an automated Auto query that fires an action when conditions are met
- Rank X accounts by their track record as callers and check the crowd's long or short lean on an asset
How do you get mcp running?
Add the hosted server URL and sign in, or run it locally with npx using an Elfa API key, or install the .mcpb file in Claude Desktop.
Follow the official instructions in the project README.
Add it to Claude Code
claude mcp add mcp -- npx -y @elfa-ai/mcp
It needs ELFA_API_KEY (a secret key). A key usually means a paid or sign-up service behind it, so check its pricing.
From the official MCP Registry (ai.elfa/mcp). Only connect MCP servers you trust: they can act on your behalf.
Make money with it
Someone could produce paid market-sentiment newsletters or research briefings using the narrative and trending data, though the data is not a guarantee of accuracy.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Track market sentiment and social attention around tokens or stocks to inform research without manual monitoring
- Set up automated market alerts for a trading-related content or analysis service, cutting time spent watching feeds
Checked 10 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.