Best for
- AI coding agents (like Claude, Cursor) that require typed security scan results.
- Development environments that need to reduce token consumption and improve output reliability.
This server is part of the Pare project, focusing on security scanning consistency. It provides structured output to improve efficiency and reliability for AI agents. Due to lack of specific tool list and client support info, users should refer to official docs for detailed configuration.
Strongest · Setup experience 9/20 Weakest · Reliability 4/20
Static review · not runListed 2026-08-07
Read the FMRS scoring method →Runtime:Node.js >=20
PARE_TOOLS
Universal tool filter across all Pare servers, formatted as comma-separated server:tool pairs (e.g. git:status); nothing to obtain externally.
{
"mcpServers": {
"pare-security": {
"command": "npx",
"args": ["-y", "@paretools/security"]
}
}
}Confirm the Pare Security server (@paretools/security, v0.22.0) appears in your client's tool list, or run npx @paretools/init doctor, then ask the agent to scan the project for vulnerabilities and check that structured JSON results come back.
Once connected, you can ask your AI assistant things like:
Pare Security is an MCP server from the Pare project that wraps Trivy security scanning and returns structured, schema-validated JSON instead of raw terminal text. It provides typed data that AI agents can act on directly, avoiding brittle string parsing. The server uses stdio transport and is distributed via the npm package @paretools/security.
Upstash's official server providing up-to-date third-party library docs for AI coding assistants
AI-powered NPM package analysis MCP server
An independent control layer that gives AI coding agents budgets, brakes, and receipts
GitHub's official MCP server for managing repos, issues, PRs, and workflows via natural language
Source revision f76328c1c7c7 Data synced 2026-10-19 Read the FMRS scoring method