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 mcp-dir/bmg-mcp --skill bmg-mcpgit clone --depth 1 https://github.com/mcp-dir/bmg-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/mcp-dir/bmg-mcp/bmg-mcp)<a href="https://agentmods.dev/skills/mcp-dir/bmg-mcp/bmg-mcp"><img src="https://agentmods.dev/badge/skills/mcp-dir/bmg-mcp/bmg-mcp/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/mcp-dir/bmg-mcp/bmg-mcp"><img src="https://agentmods.dev/badge/skills/mcp-dir/bmg-mcp/bmg-mcp.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 | $0.00053 | $0.01893 |
| Opus 5 | $0.00026 | $0.00946 |
| Sonnet 5 | $0.00011 | $0.00379 |
| Haiku 4.5 | $0.00005 | $0.00189 |
Grade A, and why
bmg-mcp scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://api.mcp.ai/api/openfinance/connectors/search \ Copies of this mod
8 near-identical copies found in the catalogue:
- neon-mcp — 97% identical, 12 lines differ
- brb-mcp — 95% identical, 12 lines differ
- necton-mcp — 95% identical, 12 lines differ
- xp-mcp — 95% identical, 12 lines differ
- safrapay-mcp — 95% identical, 12 lines differ
- redecelcoin-mcp — 95% identical, 12 lines differ
- montebravo-mcp — 95% identical, 12 lines differ
- infinitepay-mcp — 95% identical, 12 lines differ
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Banco Bmg MCP — REST API skill
Você tem acesso à Banco Bmg MCP REST API na MCP.AI.
Conecte sua conta do Banco Bmg ao Claude, ChatGPT e agentes de IA via Open Finance Brasil. Pergunte sobre saldos, extratos, faturas de cartão e investimentos do Banco Bmg em linguagem natural. Regulado pelo Banco Central, somente leitura.
Base URL
https://api.mcp.ai/api/openfinance
Todo endpoint é um POST na Base URL + o path abaixo. Os parâmetros vão no corpo JSON.
Autenticação
Inclua em toda request:
Authorization: Bearer sk_live_...
Content-Type: application/json
Gere sua chave em https://app.mcp.ai/settings/api-keys (workspace API key
sk_live_…, não expira, revogável). Uma única chave serve pra todos os seus MCPs.
Formato de resposta
{ "ok": true, "tool": "<tool_id>", "result": <payload> }
Exemplo cURL
curl -X POST https://api.mcp.ai/api/openfinance/connectors/search \
-H "Authorization: Bearer sk_live_..." \
-H "Content-Type: application/json" \
-d '{"keywords":"..."}'
Reportar problemas
Se um endpoint retornar erro, vazio ou dado inesperado, reporte (não desista calado): POST /api/openfinance/report com { "message": "...", "context"?: "...", "conversation"?: [...] }. Isso notifica o time da MCP.AI.
Endpoints (16)
openfinance_search_bank_connectors
Buscar conectores de banco (Open Finance/API) por nome (POST /api/openfinance/connectors/search)
| Parâmetro | Tipo | Obrigatório | Descrição |
|---|---|---|---|
keywords |
string[] | Sim | Termos do nome/id do banco (match OR), ex.: ['nubank','btg']. Obrigatório. |
include_accounts |
boolean | Não | Inclui contas (e contagem) de cada conexão já ligada. Custa 1 chamada por conexão; default false. |
openfinance_list_connections
Listar bancos conectados (POST /api/openfinance/connections/list)
openfinance_get_item_status
Status de uma conexão (UPDATED, LOGIN_ERROR…) (POST /api/openfinance/connections/status)
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.
- 10d ago First seen · 189 lines · 0 tokens per session scan A a1defd36dbee
bmg-mcp is a skill published in the GitHub repository mcp-dir/bmg-mcp (1 stars, last pushed 10d ago), licensed MIT. It adds 53 tokens to every session and 1,893 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.