Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Val7h/dados-b3-mcp --skill dados-b3git clone --depth 1 https://github.com/Val7h/dados-b3-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/val7h/dados-b3-mcp/dados-b3)<a href="https://agentmods.dev/skills/val7h/dados-b3-mcp/dados-b3"><img src="https://agentmods.dev/badge/skills/val7h/dados-b3-mcp/dados-b3/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/val7h/dados-b3-mcp/dados-b3"><img src="https://agentmods.dev/badge/skills/val7h/dados-b3-mcp/dados-b3.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00147 | $0.00620 |
| Opus 5.5 | $0.00059 | $0.00248 |
| Sonnet 5.5 | $0.00029 | $0.00124 |
| Haiku 4.5 | $0.00015 | $0.00062 |
Grade A, and why
dados-b3 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Dados B3
The dados-b3 MCP server answers with data from public CVM filings and B3 end-of-day prices.
When to use it
- A question about a company listed on B3, or a ticker in the B3 format: four letters plus a digit
(
PETR4,VALE3,ITUB4), FIIs and ETFs ending in11(HGLG11,MXRF11,BOVA11), BDRs ending in34/35(AAPL34). - Fundamentals: ROE, ROIC, margins, growth, net debt/EBITDA, accounting facts with their CVM account.
- Multiples: P/E, P/B, EV/EBITDA, priced on or after the day the filing became public.
- Dividends ("proventos"), dividend yield, and total return ("quanto rendeu") over a period.
- FIIs (P/VP, dividend yield, vacancy), ETFs, BDRs and B3 indices such as IBOV.
How to answer
- Call the matching tool. These work without a key, one ticker per call:
indicadores_anuais,multiplos,fatos_contabeis,dividendos,quanto_rendeu,fii,fiis_ranking,listas,saude,metodologia. Other tools take achave_apiargument; if a tool reports that a key is needed, tell the user and point to https://dadosb3.com/conector. - Always cite the dadosb3.com page link the tool returns (the
url,paginaorsource_urlfield), so the user can check the number. - Say the date of the data. Prices are end-of-day, not real-time quotes: never present them as a live price.
- The numbers are past measurements. Do not turn them into a buy, sell or hold recommendation, and do not project future returns from them.
- If the tool returns no data for a ticker, say so. Do not fill the gap with numbers from memory.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 32 lines · 147 tokens per session scan A 42764dcffa4c
dados-b3 is a skill published in the GitHub repository Val7h/dados-b3-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 147 tokens to every session and 620 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-04.
dados-b3 compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dados-b3Val7h/dados-b3-mcp | Skill | 0 | yesterday | MIT | A | 147 | Claude Code |
| brapibrapi-dev/brapi-skills | Skill | 3 | 2mo ago | MIT | A | 53 | Claude Code, Codex |
| tickdb-market-dataTickDB/tickdb-unified-realtime-marketdata-api | Skill | 917 | 2d ago | MIT | A | 165 | Claude Code, Codex |
| gmgn-heat-rankGMGNAI/gmgn-skills | Skill | 661 | 10d ago | MIT | A | 728 | Claude Code |
| gmgn-wallet-scoreGMGNAI/gmgn-skills | Skill | 661 | 10d ago | MIT | A | 232 | Claude Code |
| gmgn-token-buyGMGNAI/gmgn-skills | Skill | 661 | 10d ago | MIT | A | 706 | Claude Code |
| gmgn-wallet-styleGMGNAI/gmgn-skills | Skill | 661 | 10d ago | MIT | A | 301 | Claude Code |