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.
git clone --depth 1 https://github.com/icyberdeveloper/tbank-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/plugins/icyberdeveloper/tbank-mcp/tbank-mcp)<a href="https://agentmods.dev/plugins/icyberdeveloper/tbank-mcp/tbank-mcp"><img src="https://agentmods.dev/badge/plugins/icyberdeveloper/tbank-mcp/tbank-mcp.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
tbank 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 7d 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
{
"name": "tbank",
"displayName": "T-Bank MCP",
"version": "0.2.2",
"description": "T-Bank (Т-Банк) MCP — mobile banking API: счета, операции, заказ продуктов, переводы, мессенджер, инвестиции.",
"author": {
"name": "icyberdeveloper",
"url": "https://github.com/icyberdeveloper"
},
"homepage": "https://github.com/icyberdeveloper/tbank-mcp",
"repository": "https://github.com/icyberdeveloper/tbank-mcp",
"license": "MIT",
"keywords": [
"finance",
"banking",
"mcp",
"russian",
"tinkoff"
],
"mcpServers": {
"tbank": {
"command": "${CLAUDE_PLUGIN_ROOT}/bin/tbank-mcp",
"cwd": "${CLAUDE_PLUGIN_ROOT}"
}
},
"skills": "./tbank_mcp/skills/"
}
What it installs
The manifest is a name and a version. 11 skills, 2 MCP servers travel with it, and installing the plugin installs all of them — 1,250 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill tbank-grocery-order A 124 tokens
- Skill tbank-transfer-money A 135 tokens
- Skill tbank-tickets A 155 tokens
- Skill tbank-travel A 143 tokens
- Skill tbank-bill-pay A 96 tokens
- Skill tbank-invest-advisor A 98 tokens
- Skill tbank-budget-analyzer A 92 tokens
- Skill tbank-cards-documents A 112 tokens
- Skill tbank-messenger A 89 tokens
- Skill tbank A 110 tokens
- Skill tbank-login A 96 tokens
- MCP server tbank-mcp A not measured
- MCP server tbank A not measured
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 28 lines scan A 95e05dc32ccb
tbank is a plugin published in the GitHub repository icyberdeveloper/tbank-mcp (25 stars, last pushed 10d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
banco-inter-api
Skill não oficial para integrações com APIs do Banco Inter: OAuth/mTLS, Banking, Pix, Cobrança, webhooks, CNAB, crédito e troubleshooting.
jaz-ai
Complete AI agent stack for Jaz Accounting. 369 tools, 159 API rules, 13 IFRS recipes, 13 calculators, 12 job playbooks. Jaz Kit multi-organization workspaces with resumable closes. Data migration (Xero/QB/Sage/MYOB). Singapore Form C-S tax. For Claude Code, Copilot, Cursor, Codex, and any MCP-compatible agent.
agentrisk
Risk guardrails for AI trading agents. Your agent proposes; your policy decides.
coinpaprika
Access cryptocurrency market data from CoinPaprika: real-time prices, OHLCV, exchanges, contract lookups for 12,000+ cryptocurrencies and 350+ exchanges. Free tier, no API key needed.
monzo
Read-only Monzo banking integration — balances, transactions, pots, and spending analysis via MCP server.
vivid-mcp
Open a Vivid Business account from your AI chat via MCP.