echo-sentiment-mcp
Provides real-time XLM (Stellar) market sentiment as a tool, computed from a keyless composite of the Crypto Fear & Greed Index, SDEX order-flow imbalance, and 24h price momentum. Enables users to get deterministic sentiment scores and market data without any API keys or paid data feeds.
README
Echo Sentiment — MCP Server (XLM Market Sentiment)
A Model Context Protocol (MCP) server that exposes real-time XLM (Stellar) market sentiment as a tool, computed from a keyless composite:
- Crypto Fear & Greed Index (public API, no key)
- Stellar SDEX order-flow imbalance (public order book)
- 24h price momentum (CoinGecko public API)
No LLM in the loop, no API keys, no paid data feeds. Rules + math only.
Hosted endpoint (pay-per-call via x402)
Prefer using it rather than self-hosting? The same tool runs live at:
https://abstain-eliminate-unison.ngrok-free.dev/mcp
The full REST API behind it also offers /v1/sentiment, /v1/quote,
/v1/arb-opportunities, /v1/multi-asset and a premium
/v1/sentiment-report, all pay-per-call in USDC on Base via the
x402 protocol (HTTP 402 → sign an EIP-3009 permit →
retry → 200). See /llms.txt
for the machine-readable summary.
Tool
get_xlm_sentiment → JSON string:
{
"sentiment": -0.45,
"sentiment_source": "FNG(30)+flow(-0.75)+mom(+0.39%)",
"components": {"FNG(30)": -0.4, "flow(-0.75)": -0.75, "mom(+0.39%)": 0.078},
"price_usd": 0.1619,
"mid": 0.1620,
"spread_pct": 0.09,
"ts": 1786158508.1
}
sentiment is in [-1, 1]: positive = bullish, negative = bearish.
Self-host
pip install -r requirements.txt
python mcp_bridge.py # serves streamable HTTP MCP on 127.0.0.1:8010
Connect any MCP client (Claude Desktop, Cursor, custom agents) to
http://127.0.0.1:8010/mcp (or run it behind your own HTTPS).
Why
- Rules-based: deterministic scores, no model drift, cheap to run.
- Keyless: nothing to sign up for, nothing to leak.
- Composite: three independent signals weighted 0.3/0.4/0.3
(configurable via
SENTIMENT_WEIGHT_*env vars).
License
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.