mcpindex.aiv0
← Index

Aegis

io.github.verrysimatupang99/aegis·v0.1.1·Security
Quality Score
85
/100

Charter-bound defensive security copilot: secrets, obfuscation, deps, Dockerfile, IaC scans.

Repository →
§00  Trust verdict · v1 advisory ·  method
UNVERIFIEDno verdict on file

Verdict not yet evaluated for this tool. The hybrid eval runs adversarial cases first; coverage rolls out as the corpus expands. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: hybrid eval, four-state verdict, honest limits.

§01  Install
Claude Desktop (uvx)
{
  "mcpServers": {
    "aegis": {
      "command": "uvx",
      "args": [
        "aegis-sec"
      ],
      "env": {
        "AEGIS_HOME": "<aegis_home>",
        "ANTHROPIC_API_KEY": "<your-anthropic_api_key>"
      }
    }
  }
}
§02  Environment variables
AEGIS_HOME

Project root containing data/mythos.yaml. Defaults to current working directory.

ANTHROPIC_API_KEY
secret

Optional. Only needed if you call the `aegis advise` cloud LLM path.

§03  MCP Quality Score  ·  methodology
freshness
25
completeness
15
installability
25
documentation
15
stability
5
§04  Alternatives in Security
Helixar Security
ai.helixar/mcp

Security tools for AI agents: scan MCP servers, validate HDP delegation chains, audit releases.

ai.smithery/Nekzus-npm-sentinel-mcp
ai.smithery/Nekzus-npm-sentinel-mcp

Provide AI-powered real-time analysis and intelligence on NPM packages, including security, depend…

app.zenable/zenable
app.zenable/zenable

Zenable cleans up sloppy AI code and prevents vulnerabilities with deterministic guardrails