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/RanjithKumarSeekolu/dejankWrote 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/ranjithkumarseekolu/dejank/dejank)<a href="https://agentmods.dev/mcp/ranjithkumarseekolu/dejank/dejank"><img src="https://agentmods.dev/badge/mcp/ranjithkumarseekolu/dejank/dejank/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/ranjithkumarseekolu/dejank/dejank"><img src="https://agentmods.dev/badge/mcp/ranjithkumarseekolu/dejank/dejank.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dejank 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 8d 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
{ "dejank": { "command": "npx", "args": [ "-y", "dejank" ] } }
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.
- 8d ago First seen · 9 lines scan A 287ceaca4c7a
dejank is an MCP server published in the GitHub repository RanjithKumarSeekolu/dejank (0 stars, last pushed 19d 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
deepadb
Full-featured ADB MCP server — 209 tools across 49 modules, from UI to baseband. Runs locally from the deepadb npm package.
rn-devtools-hub
Drive a running React Native or Expo app from inside its JS runtime: see, act, prove. Runs locally from the rn-devtools-hub npm package.
adb
MCP server "adb" as configured in iksnerd/adb-mcp. Launched with adb-mcp.
android-mcp-adb
Full Android control from any AI agent via MCP — 7 tools, 90fps viewer, WiFi ADB. Runs locally from the android-mcp-adb Python package.
adb-mcp-server
MCP server for Android Debug Bridge (ADB) — manage connected devices, run shell commands, view logcats, query SQLite databases and more. Runs locally from the @abhinavyadav/adb-mcp-server npm package.
XcodeBuildMCP
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities. Runs locally from the xcodebuildmcp npm package. Needs 4 environment variables to run.