About 熔岩 Lava · A股机构/大V消息面热度监测
Lava provides structured news-heat data for China A-share stocks and concept sectors, for quantitative systems and agents. The data is read-only; institutions and influencers use anonymous IDs, and results exclude original text and long-or-short direction.
Key features
- 01Check stock news heat
- 02Search structured news records
- 03View concept and stock mention rankings
- 04Query anonymous agency scores and history
- 05Check account balance and usage
Use cases
- 01Monitor recent news heat for A-share stocks
- 02Compare stock mentions within a concept sector
- 03Review current anonymous agency scores and changes
MCP support
A remote Streamable HTTP MCP server exposes tools for stock and concept heat, structured news search, anonymous agency scores, and account usage. Authentication uses a Bearer Token or X-API-Key.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://lava.ai-dolphin.com/subscribe/v1/mcpclaude mcp add --transport http dustinliang666-blip-lava https://lava.ai-dolphin.com/subscribe/v1/mcp{"mcpServers":{"dustinliang666-blip-lava":{"type":"http","url":"https://lava.ai-dolphin.com/subscribe/v1/mcp"}}}Open in Cursor{"servers":{"dustinliang666-blip-lava":{"type":"http","url":"https://lava.ai-dolphin.com/subscribe/v1/mcp"}}}Open in VS Code{"mcpServers":{"dustinliang666-blip-lava":{"type":"http","url":"https://lava.ai-dolphin.com/subscribe/v1/mcp"}}}{"mcpServers":{"dustinliang666-blip-lava":{"serverUrl":"https://lava.ai-dolphin.com/subscribe/v1/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://lava.ai-dolphin.com/subscribe/v1/mcpAuth requiredTools
Details
From the project READMElava-mcp · 熔岩消息面热度监测
熔岩（Lava） 提供 A 股股票和概念板块的消息面热度监测 结构化只读数据——量化交易必备的消息面热度信号，供系统与智能体通过远程 MCP / REST 调用。
只读 · 结构化要点 + 匿名机构/大V ID · 不含多空方向与原文 · 不构成投资建议
新手 3 步
① 开通并复制 API Key（登录熔岩 → 左侧「AI数据服务」→ API Key → 新建）
② 装 Skill，或在豆包办公/WorkBuddy/千问办公填 MCP 地址 https://lava.ai-dolphin.com/subscribe/v1/mcp
③ 用中文问「某某股票最近消息面热不热」
远程 MCP（推荐）
| 项 | 值 |
|---|---|
| 传输 | Streamable HTTP |
| Endpoint | https://lava.ai-dolphin.com/subscribe/v1/mcp |
| 鉴权 | 请求头 Authorization: Bearer <API Key>（或 X-API-Key） |
| 客户端 | 豆包办公、WorkBuddy（BUDDY）、千问办公（QwenWork）等支持自定义 HTTP MCP 的客户端 |
开通与计费见 落地页：开通赠 100 元代金券；1000 次 = 5 元。
Skill 模板
仓库内 SKILL.md 与官方模板一致，也可直接读取：
https://lava.ai-dolphin.com/subscribe/v1/skill
适用于固化「查个股/概念消息面热度」流程。
文档与机器可读规范
- 产品落地页：https://lava.ai-dolphin.com/subscribe
- API 文档（canonical）：https://lava.ai-dolphin.com/subscribe/docs
- OpenAPI 3.0：https://lava.ai-dolphin.com/subscribe/v1/openapi.json
- llms.txt：https://lava.ai-dolphin.com/llms.txt
- MCP Registry：
server.json - Glama：
glama.json
主要工具（MCP）
| Tool | 用途 |
|---|---|
get_stock_news_heat | 个股消息面热度与结构化观点列表 |
search_news_flow | 关键词检索消息面结构化记录 |
get_concept_stock_heat | 概念 → 个股提及排行 |
get_stock_concept_heat | 个股 → 概念提及排行 |
get_agency_ranking / get_agency_pit / get_agency_history / list_agency_pit_dates | 匿名机构/大V评分（当前 / PIT / 时序） |
get_account | 余额与用量（不计费） |
合规边界
- 勿将输出写成荐股、多空或收益承诺
- 机构/大V仅使用匿名
agency_id，勿猜测真实机构/大V名 - 勿外推控制台路径（
/subscribe/v1/console为 noindex）
License
文档与 Skill 模板以站点公开内容为准；本仓库仅作接入说明与分发入口。
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.