# 熔岩 Lava · A股机构/大V消息面热度监测

> 熔岩 Lava · A股机构/大V消息面热度监测 is an MCP server for finance and payments. Read-only China A-share data on how often institutions and influencers mention a stock. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Free trial
- **Platforms:** API, Web
- **Website:** https://lava.ai-dolphin.com/subscribe/docs
- **Repository:** https://github.com/dustinliang666-blip/lava-mcp
- **MCP Registry name:** io.github.dustinliang666-blip/lava-mcp
- **Categories:** finance and payments, analytics and data
- **Listing updated:** 2026-11-15

## About

Lava (熔岩) monitors how often institutions and well-known commentators mention A-share stocks and concept sectors, and reports the key points. Institution and influencer identities appear only as anonymous `agency_id` values, and news hits carry no headlines or body text.

The remote server offers 18 tools covering per-stock heat, windowed counts, a market-wide hot list, accelerating names, first-mention stocks, weighted rankings, daily heat panels, agency coverage and scoring history. Documentation also describes REST access and OpenAPI.

Authentication is an API key or OAuth 2.1. The docs advise calling the free `get_account` first to verify the connection. Sector trend and sentiment views are on the website; subscription access to them is still planned.

## Features

- **Stock news heat:** Mentions, institution counts and summary points for one stock.
- **Concept heat:** Hot concept sectors and stock-to-concept lookups.
- **Market hot lists:** Hot, accelerating, first-mention and weighted lists.
- **Agency scoring:** Anonymous institution scores with point-in-time history.
- **Daily panels:** Daily series for backtesting and export.

## Good for

- Check how heavily a stock was discussed this week
- Find concept sectors drawing the most mentions
- Feed a quant research workflow with mention data
- Spot stocks mentioned for the first time

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http lava-mcp https://lava.ai-dolphin.com/subscribe/v1/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://lava.ai-dolphin.com/subscribe/v1/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "lava-mcp": {
      "url": "https://lava.ai-dolphin.com/subscribe/v1/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "lava-mcp": {
      "type": "http",
      "url": "https://lava.ai-dolphin.com/subscribe/v1/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "lava-mcp": {
      "serverUrl": "https://lava.ai-dolphin.com/subscribe/v1/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "lava-mcp": {
      "type": "http",
      "url": "https://lava.ai-dolphin.com/subscribe/v1/mcp"
    }
  }
}
```

## Tools

- `get_account`: Free connection check
- `get_stock_news_heat`: Mentions and summary points for a stock
- `get_stock_heat_windows`: Heat across time windows
- `search_news_flow`: Search news flow
- `get_market_hot_concepts`: Hot concept ranking
- `get_concept_stock_heat`: Stocks within a concept
- `get_stock_concept_heat`: Concepts for a stock
- `get_market_hot_stocks`: Market hot list
- `get_accelerating_hot_stocks`: Accelerating stocks
- `get_first_mention_stocks`: First-mention stocks
- `get_weighted_hot_stocks`: Score-weighted hot list
- `get_stock_heat_panel`: Daily heat panel
- `get_agency_coverage`: Agency coverage counts
- `get_news_stock_hits`: News hits by stock, no text
- `get_agency_ranking`: Agency ranking
- `get_agency_pit`: Point-in-time agency scores
- `get_agency_history`: Agency score history
- `list_agency_pit_dates`: Available point-in-time dates

## FAQ

### Is data identifiable?

No. Institutions and influencers use anonymous agency IDs.

### What does it cost?

A 100 yuan voucher on signup, then about 5 yuan per 1,000 requests.

### Which calls are free?

initialize, tools/list, ping and get_account are not billed.

### How do I sign in?

An API key (lvk_ prefix) or OAuth 2.1.

### Is 熔岩 Lava · A股机构/大V消息面热度监测 free?

熔岩 Lava · A股机构/大V消息面热度监测 is a paid product with a free trial.

### How do I add 熔岩 Lava · A股机构/大V消息面热度监测 to Claude Code?

Run this command in your terminal: claude mcp add --transport http lava-mcp https://lava.ai-dolphin.com/subscribe/v1/mcp

### What are the best alternatives to 熔岩 Lava · A股机构/大V消息面热度监测?

The closest alternatives to 熔岩 Lava · A股机构/大V消息面热度监测 are Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP, Solana MCP by Vybe, Tapetide - Indian Stock Market MCP and World Monitor.

## Alternatives

- [Agent-Native Analytics](https://ai-powered.com/mcp/agent-native-analytics): Agent-Native Analytics is an open-source MCP server for analytics and data.
- [Google Ads + Meta Ads + SEO/GEO MCP](https://ai-powered.com/mcp/google-ads-meta-ads-seo-geo-mcp): Google Ads + Meta Ads + SEO/GEO MCP is a freemium MCP server for marketing and seo.
- [Solana MCP by Vybe](https://ai-powered.com/mcp/solana-mcp-by-vybe): Solana MCP by Vybe is an MCP server for finance and payments.
- [Tapetide - Indian Stock Market MCP](https://ai-powered.com/mcp/tapetide-indian-stock-market-mcp): Tapetide - Indian Stock Market MCP is a freemium MCP server for finance and payments.
- [World Monitor](https://ai-powered.com/mcp/world-monitor): World Monitor is a freemium MCP server for analytics and data.
- [Budget Tracker](https://ai-powered.com/mcp/budget-tracker-2): Budget Tracker is a freemium MCP server for finance and payments.
- [CompanyData](https://ai-powered.com/mcp/companydata): CompanyData is a paid MCP server for analytics and data.
- [ChartAnt](https://ai-powered.com/mcp/chartant): ChartAnt is a freemium MCP server for design and media.

---
Source: https://ai-powered.com/mcp/lava-a-v
