io.github.jnMetaCode/shellward
Quality Score
79
/100
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
§01 Install
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"shellward": {
"command": "npx",
"args": [
"-y",
"shellward"
],
"env": {
"SHELLWARD_MODE": "<shellward_mode>",
"SHELLWARD_LOCALE": "<shellward_locale>",
"SHELLWARD_THRESHOLD": "<shellward_threshold>"
}
}
}
}Cursor (.cursor/mcp.json)
{
"mcpServers": {
"shellward": {
"command": "npx",
"args": [
"-y",
"shellward"
],
"env": {
"SHELLWARD_MODE": "<shellward_mode>",
"SHELLWARD_LOCALE": "<shellward_locale>",
"SHELLWARD_THRESHOLD": "<shellward_threshold>"
}
}
}
}Cline (cline_mcp_settings.json)
npx -y shellward§02 Environment variables
SHELLWARD_MODESecurity mode: enforce (block + log) or audit (log only)
SHELLWARD_LOCALELocale: auto, zh, or en
SHELLWARD_THRESHOLDInjection detection threshold 0-100 (lower = stricter)
§03 MCP Quality Score · methodology
freshness
24
completeness
10
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