Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add cyberkaida/reverse-engineering-assistant/plugin install ReVaWrote 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/cyberkaida/reverse-engineering-assistant/reva)<a href="https://agentmods.dev/mcp/cyberkaida/reverse-engineering-assistant/reva"><img src="https://agentmods.dev/badge/mcp/cyberkaida/reverse-engineering-assistant/reva.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
ReVa 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 4d 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
{
"ReVa": {
"command": "uv",
"args": [
"run",
"mcp-reva"
],
"env": {
"UV_WORKING_DIRECTORY": "${CLAUDE_PLUGIN_ROOT}/../"
}
}
}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.
- 4d ago First seen · 12 lines scan A dda00d8088a5
ReVa is an MCP server published in the GitHub repository cyberkaida/reverse-engineering-assistant (821 stars, last pushed 9d ago), licensed Apache-2.0. 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
reversecore-mcp
A security-first MCP server that empowers AI agents to perform automated reverse engineering, malware analysis, forensics, vulnerability research, and SAST — powered by Radare2, YARA, LIEF, Capstone, and more. Runs locally from the reversecore-mcp Python package.
ghidra-bizhawk-mcp
MCP server "ghidra-bizhawk-mcp" as configured in getanirao/ghidra-bizhawk-mcp. Runs locally from the ghidra-bizhawk-mcp Python package. Needs 3 environment variables to run.
rbinmcp
MCP server "rbinmcp" as configured in kirkderp/rbinmcp. Runs in Docker (ghcr.io/kirkderp/rbinmcp:1.3.0).
codecartographer
Turn an unfamiliar codebase into validated architecture, contracts, and a reimplementation spec. Runs locally from the codecartographer-pi npm package.
white-hat-agent
MCP server "white-hat-agent" as configured in kappa9999/white-hat-agent. Runs locally from the white-hat-agent Python package.
metabase-ai-assistant
The most powerful MCP Server for Metabase - 134 tools with structured output, AI-powered SQL generation, dashboard automation, user management & enterprise BI. MCP SDK v1.26.0 compliant. Works with Claude, Cursor, and any MCP-compatible AI. Runs locally from the metabase-ai-assistant npm package. Needs 9 environment…