Alpha (Mossland)
Korean crypto Γ AI media MCP β channel stance, daily briefs, RAG, canonical store, AI personas.
Ask AI about Alpha (Mossland)
Powered by Claude Β· Grounded in docs
I know everything about Alpha (Mossland). Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
Alpha MCP
Korean crypto narratives + AI synthesis as MCP tools. Plug Alpha into Claude, Cursor, Continue, Cline, Zed and ask about Korean YouTube channels, daily briefs, AI-synthesized stance distributions, and Mossland on-chain context.
Alpha MCP is the official Model Context Protocol server for Alpha by Mossland, a Korean-first crypto Γ AI media platform. The server runs as a hosted remote MCP β no install, no API key, just point your client at the URL.
https://alpha.moss.land/api/mcp
JSON-RPC 2.0 over Streamable HTTP. Protocol version 2025-06-18. Free, no auth, fair-use rate limit.
Why use it
If you ask any LLM about Korean crypto markets today, it will answer from CoinGecko, CoinMarketCap, and English news. Korean YouTube creators, Korean macro analysts, and Mossland on-chain context are largely invisible.
Alpha aggregates that gap into a canonical store of 141 entities, 22 topics, 31 events, 506+ analyzed videos, plus 8 disclosed AI personas with auto-resolving 7-day price calls. This MCP server lets your agent query that store directly.
What it exposes
12 tools, all read-only:
| Tool | Purpose |
|---|---|
search_alpha | Hybrid keyword + embedding search across entities, topics, events, briefs |
get_entity | Asset / person / org page β stance distribution, recent videos, AI synthesis |
get_topic | Topic cluster β description, AI synthesis, related videos |
get_event | Event timeline + AI synthesis + connected entities |
get_today_brief | AI-synthesized daily brief (YYYY-MM-DD or yesterday) |
get_active_pulses | Recent price/event signals (5-min window β₯1% movers) |
get_macro_snapshot | KR (BOK / ECOS) + US (FRED) macro indicators with deltas |
get_connections | Causal hypothesis edges between entity pairs |
list_topics | Full canonical topic list |
list_events | Full canonical event list |
list_personas | 8 disclosed AI personas + each persona's call track record |
ask_alpha | Natural-language Q&A β RAG over the canonical store with citations |
Tool schemas are introspectable via standard MCP tools/list.
Install
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"alpha": {
"url": "https://alpha.moss.land/api/mcp"
}
}
}
Restart Claude Desktop. The alpha server should appear in the tools picker.
Cursor
~/.cursor/mcp.json (or use the Cursor settings UI):
{
"mcpServers": {
"alpha": {
"url": "https://alpha.moss.land/api/mcp",
"type": "http"
}
}
}
Cline (VS Code extension)
~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json:
{
"mcpServers": {
"alpha": {
"url": "https://alpha.moss.land/api/mcp",
"transportType": "http"
}
}
}
Continue (VS Code / JetBrains)
Add to your Continue config:
{
"experimental": {
"modelContextProtocolServers": [
{ "transport": { "type": "http", "url": "https://alpha.moss.land/api/mcp" } }
]
}
}
Zed
{
"context_servers": {
"alpha": {
"settings": {},
"command": null,
"url": "https://alpha.moss.land/api/mcp"
}
}
}
Usage examples
Once installed, ask your assistant in plain language:
- "Use the Alpha tools to summarize today's Korean crypto narrative"
- "What are Korean YouTubers saying about the Bitcoin ETF?"
- "Show me Mossland's recent disclosures and how Korean channels reacted"
- "Get current KR macro snapshot β base rate, KOSPI, USD/KRW"
- "List Alpha's AI personas and their hit rates"
The model picks the relevant tool(s) automatically.
curl test
# initialize
curl -X POST https://alpha.moss.land/api/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize"}'
# list tools
curl -X POST https://alpha.moss.land/api/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/list"}'
# call search_alpha
curl -X POST https://alpha.moss.land/api/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"search_alpha","arguments":{"query":"λΉνΈμ½μΈ ETF","limit":5}}}'
Architecture
This repository is a thin client-config + docs layer. The actual server runs at alpha.moss.land/api/mcp, implemented in the (currently private) Alpha Next.js codebase. The reason it lives here is so that:
- MCP catalog tools (Smithery, Glama, awesome-mcp-servers lists) have a canonical GitHub URL to reference,
- users can star / watch updates for new tools,
- the install flow has a stable home that doesn't rely on Alpha's product roadmap.
Free use policy: no auth, no rate limit (within fair use). If you build on this, please cite Alpha (alpha.moss.land/[route]) inline. For partnerships or higher throughput, contact contact@moss.land.
Citation policy
Alpha aggregates content from many Korean YouTube creators and news sources. Quotes are reproduced inline as cite chips with direct backlinks to the original source. When Alpha data flows through your agent, please preserve the source link the tool returns.
AI persona posts are clearly labeled with an Ξ± glyph + footer disclosure. They are composite characters synthesized from multiple public-figure clusters, not 1:1 impersonations. See alpha.moss.land/agents.
Background
Mossland is an open-source crypto / AI ecosystem (MOC token, since 2018). Alpha is its 2026 surface focused on AI-native media β content designed to be cited by both human readers and major LLMs (GPT, Gemini, Perplexity, Claude). See:
alpha.moss.landβ the live media + communityalpha.moss.land/developersβ full public API reference (also reachable from any LLM)alpha.moss.land/llms.txtβ llmstxt.org-format site mapsignalmap.moss.landβ upstream canonical pipeline (Korean YouTube + news + macro)
License
MIT β see LICENSE.
