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/m-binimran/design-packWrote 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/mcp/m-binimran/design-pack/nano-banana)<a href="https://agentmods.dev/mcp/m-binimran/design-pack/nano-banana"><img src="https://agentmods.dev/badge/mcp/m-binimran/design-pack/nano-banana/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/mcp/m-binimran/design-pack/nano-banana"><img src="https://agentmods.dev/badge/mcp/m-binimran/design-pack/nano-banana.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
nano-banana 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 2mo 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
{
"nano-banana": {
"command": "npx",
"args": [
"-y",
"REPLACE_WITH_NANOBANANA_MCP_PACKAGE"
],
"env": {
"GEMINI_API_KEY": "your-gemini-api-key"
}
}
}What else .mcp.json configures
This page is one entry in a file that holds 7. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- 2mo ago First seen · 12 lines scan A b5aa3fff331d
nano-banana is an MCP server published in the GitHub repository m-binimran/design-pack (4 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-08-31.
Other mcp servers, from other repositories
pullpush-mcp
Connect any two APIs and keep them in sync — 48 MCP tools with shadow previews and diagnostics. Runs locally from the kaduno-pullpush-mcp npm package. Needs 2 environment variables to run.
microsoft-graph-enterprise
MCP server "microsoft-graph-enterprise", hosted remotely at mcp.svc.cloud.microsoft, as configured in daddia/claude-for-strategy.
atlassian
MCP server "atlassian", hosted remotely at mcp.atlassian.com, as configured in daddia/claude-for-strategy.
notion
Notion's hosted MCP server: lets the agent search, read and edit pages and databases. Remote server at mcp.notion.com.
power-bi
MCP server "power-bi", hosted remotely at api.fabric.microsoft.com, as configured in daddia/claude-for-strategy.
slack
Slack's hosted MCP server: lets the agent read channels, search messages and post in a Slack workspace. Remote server at mcp.slack.com.