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/wagonbomb/kawaiidra-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/mcp/wagonbomb/kawaiidra-mcp/kawaiidra)<a href="https://agentmods.dev/mcp/wagonbomb/kawaiidra-mcp/kawaiidra"><img src="https://agentmods.dev/badge/mcp/wagonbomb/kawaiidra-mcp/kawaiidra/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/wagonbomb/kawaiidra-mcp/kawaiidra"><img src="https://agentmods.dev/badge/mcp/wagonbomb/kawaiidra-mcp/kawaiidra.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
kawaiidra 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 12d 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
{
"kawaiidra": {
"command": "python",
"args": [
"run_server.py"
],
"env": {
"GHIDRA_INSTALL_DIR": "${GHIDRA_INSTALL_DIR}"
}
}
}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.
- 12d ago First seen · 11 lines scan A 31e34e52990e
kawaiidra is an MCP server published in the GitHub repository wagonbomb/kawaiidra-mcp (15 stars, last pushed 6mo 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 2026-08-30.
Other mcp servers, from other repositories
rea
Reverse engineer anything from your terminal or agent with one CLI and MCP server. Runs locally from the rea-agents npm package.
ghidralens
Interactive Ghidra views in your AI client: decompile, rename, and navigate a binary. Runs locally from the ghidralens npm package. Needs 2 environment variables to run.
idamesh
A Model Context Protocol server for IDA Pro. Runs locally from the idamesh Python package. Needs 1 environment variable to run.
ida-pro-mcp-fusion
MCP server "ida-pro-mcp-fusion" as configured in rison1337/ida-pro-mcp-fusion. Launched with https://github.com/rison1337/ida-pro-mcp-fusion/releases/download/v2.0.0/ida-pro.
ghidra-mcp
MCP server "ghidra-mcp" as configured in bethington/ghidra-mcp. Runs locally from the c:/Users/benam/source/mcp/ghidra-mcp Python package. Needs 3 environment variables to run.
x64dbg
MCP server for x64dbg debugger - 23 mega-tools for AI-powered reverse engineering and debugging. Runs locally from the x64dbg-mcp-server npm package. Needs 2 environment variables to run.