How AI Agents Pull A-Share Heat Data via MCP in About Five Minutes

Lava (熔岩), a read-only data service, exposes structured A-share stock and concept-board heat signals over both MCP and a REST API sharing a single schema, letting LLM agents query market attention data in minutes. The service counts and weights mentions across institutional notes, commentators and mainstream financial news, anonymizing sources into stable IDs, and offers tools for hot stocks, accelerating heat, first mentions, per-stock heat windows, concept mappings, source coverage and daily panels for backtests. It returns attention data only, with no bullish/bearish labels, original text or price targets.

Most LLM agents that touch Chinese equities hit the same wall: the model can reason about a sector, but it has no structured, timely view of what the market is actually talking about . Scraping forums and news sites is brittle, slow, and full of raw text you probably should not be redistributing. Lava 熔岩 is a read-only data service that turns A-share news flow into structured heat signals for stocks and concept boards, exposed over both MCP and REST. This post walks through what the data means, which tools exist, and how to wire an agent to it quickly. Lava returns attention/heat data only. No bullish/bearish labels, no original text, no price targets, and nothing in this article is investment advice. Lava counts and weights mentions of A-share stocks and concept boards across institutional notes, commentators, and mainstream financial news. Sources are anonymized into stable IDs for example an agency ID , so you can track source quality without seeing names or source text. Three data categories matter most for agents: A-share narratives move through concept boards AI computing, solid-state batteries, low-altitude economy, etc. . Lava tracks: Comparing those across windows gives you a rotation view: attention leaving one board and arriving at another. A first-mention is a stock that had zero mentions in the previous 7 days and just got its first one. It is a novelty signal: useful for "what entered the conversation today" digests, and a natural input for research triage. The MCP server and the REST API share one schema. Tool names below match the OpenAPI operationId s, so an agent can resolve them deterministically. | Tool operationId | Path | Key params | Returns | |---|---|---|---| | listHotStocks | GET /hot/stocks | window , market , min score , limit | Most-mentioned stocks in window | | listHotConcepts | GET /hot/concepts | window , min score , limit | Hottest concept boards | | listWeightedHotStocks | GET /hot/weighted | as of date , days , min score , order , market , limit | Heat weighted by source score | | listAcceleratingHotStocks | GET /hot/accelerating | window , order , min mentions , market , limit | Momentum-sorted heat changes | | listFirstMentions | GET /hot/first-mentions | hours , min score , limit | Stocks first mentioned after 7 quiet days | | Tool | Path | Key params | Returns | |---|---|---|---| | getStockHeatWindows | GET /heat/windows | stock name or ts code , min score | Heat for 1h…7d windows + hourly last 24h | | listOpinionsByStock | GET /opinions | ts code , days , start date , end date , only this stock , limit | Mention records structured, no text | | listConceptStocks | GET /concepts/stocks | concept , days , limit | Top-mentioned stocks inside a concept | | listStockConcepts | GET /concepts/by-stock | ts code , days , limit | Hottest concepts linked to a stock | | getStockAgencyCoverage | GET /coverage/stocks | ts code , days , min score | Source-coverage time series | | listNewsStockHits | GET /news/hits | ts code , hours , src , limit | Stocks named in mainstream news | | Tool | Path | Key params | Returns | |---|---|---|---| | getDailyHeatPanel | GET /panel/daily | type , codes , names , from , to | Daily panel mentions, source count, weighted heat for backtests | | listAgencyRanking | GET /agencies/ranking | order , min score , limit , offset | Current source scores | | listAgencyPit | GET /agencies/pit | as of date , agency id , min score | Point-in-time source scores | | getAgencyHistory | GET /agencies/{agency id}/history | start date , end date | Score history of one source | | searchOpinions | GET /opinions/search | keyword , since , limit | Keyword search over mention records | | getAccount | GET /account | — | Balance and usage free call | ts code uses the Tushare-style format, e.g. 300750.SZ , 688256.SH . Point-in-time PIT scores matter if you backtest: listAgencyPit gives source scores as they were on as of date , so weighted heat in your backtest does not leak future information. Sign up, copy your API key format lvk … , and note the MCP endpoint URL from the docs. Keys go in a header: Authorization: Bearer lvk xxxxxxxx Never commit the key; read it from an environment variable. Most MCP clients Claude Desktop, Cursor, Cline, custom agents accept a remote HTTP server entry like this: { "mcpServers": { "lava": { "url": "<LAVA MCP URL ", "headers": { "Authorization": "Bearer ${LAVA API KEY}" } } } } Restart the client; it should list the tools above. Call getAccount first. It costs nothing and confirms auth. Then try: listHotConcepts window="24h", limit=10 If your agent framework does not speak MCP, the same data is plain HTTP: curl -s "$LAVA BASE/hot/first-mentions?hours=24&min score=60&limit=20" \ -H "Authorization: Bearer $LAVA API KEY" python import os, requests BASE = os.environ "LAVA BASE" H = {"Authorization": f"Bearer {os.environ 'LAVA API KEY' }"} def lava path, params : r = requests.get f"{BASE}{path}", headers=H, params=params, timeout=20 r.raise for status return r.json concepts = lava "/hot/concepts", window="24h", limit=10 Goal: a short brief of "what the market is discussing", generated before the open. listHotConcepts window="24h", limit=10 → top boards. listConceptStocks concept=..., days=1, limit=5 . listFirstMentions hours=24, min score=60, limit=10 → new names. listAcceleratingHotStocks window="24h", min mentions=3, limit=10 → movers in attention. Prompt the model to describe attention only: "rank by heat, note rotation versus yesterday, list first-mentions". Instruct it explicitly not to produce buy/sell language. Run listHotConcepts at window="24h" and window="7d" and diff the ranks. A concept high on 24h but low on 7d is newly rotating in; the reverse is cooling off. Store daily snapshots, or skip the bookkeeping and pull getDailyHeatPanel type="concept", names=... for history. When a user asks about a ticker, have the agent fetch: getStockHeatWindows ts code=... for the 1h–7d curve; listStockConcepts ts code=..., days=7 for which narratives it is riding; getStockAgencyCoverage ts code=..., days=30, min score=60 to see if coverage breadth is growing or shrinking. This gives the model grounded context "heat is concentrated in the last 6 hours, mainly via the AI computing board, with coverage from more high-score sources than last week" instead of hallucinated sentiment. min score ts code over names limit and avoid loops that fan out over every stock in a board. If you want to see the data before writing code, the AI board heat monitor https://lava.ai-dolphin.com/monitor/board-ai-heat https://lava.ai-dolphin.com/monitor/board-ai-heat shows a concept heat series built from these same endpoints. An agent with Lava attached can answer "what is the A-share market paying attention to, and how is that changing?" with structured numbers instead of guesses. Setup is one header and one server entry; the useful part is combining heat, concept rotation, and first-mention into workflows. Research notes, methodology, and worked examples are here: https://lava.ai-dolphin.com/research https://lava.ai-dolphin.com/research