MCP-INDEX

◆ LLM analysis failed. Retry

dreadnode/capabilitiescritical

Public source of the Dreadnode capabilities in app.dreadnode.io — agents, tools, skills, MCP servers, and workers.

This repository provides a collection of MCP servers and tools for AI red-teaming and security operations, including BloodHound CE graph queries, Ghos...

purpose: This repository provides a collection of MCP servethreat: local with credentials

Python · ★ 6 · Jun 20, 2026 · ⚙ Jun 9, 2026 · GITHUB ↗

heuristic signalsshell.exec network.http slack.integration env.exposure aws.integration filesystem.read filesystem.write auth.none browser.automation github.access

RISK SCORE

0/ 100 risk

high findings+75

medium findings+75

capped at100

Indicators — descriptive signals, not vulnerabilities

dynamic-importcapabilities/binary-analysis/mcp/ghidra_mcp.py:206 lambda: __import__(

dynamic-importcapabilities/binary-analysis/mcp/ghidra_mcp.py:212 lambda: __import__("ghidra.app.emulator", fromlist=["EmulatorHelper"]),

dynamic-importcapabilities/binary-analysis/mcp/ghidra_mcp.py:216 lambda: __import__(

dynamic-importcapabilities/binary-analysis/mcp/ghidra_mcp.py:222 lambda: __import__(

These are automated indicators of code characteristics detected by regex pattern matching. They are informational, not security verdicts. Some patterns (e.g. telegram, crypto-wallet) may reflect legitimate functionality.

Analysis failed

Findings are produced by automated LLM analysis and may include false positives or miss issues. Verify independently before acting.