Best for
- TypeScript/JavaScript projects using npm or pnpm
- Integration with AI coding assistants that need type-safe command outputs
- Development environments that want to reduce errors from CLI output parsing
This server focuses on providing structured JSON output for npm/pnpm operations, suitable for AI agent integration. It is not an official npm server but a community project. Its main strengths are token efficiency and reliability, but it requires Node.js 20+ and only supports npm/pnpm.
Strongest · Maintenance 12/20 Weakest · Reliability 6/20
Static review · not runListed 2026-08-07
Read the FMRS scoring method →Runtime:Node.js 20+
PARE_NPM_TOOLS
Optional per-server filter limiting which tools the npm server registers, e.g. install,test,run; unset means all tools.
PARE_TOOLS
Optional universal filter across all Pare servers in server:tool comma-separated format, e.g. git:status,npm:install; takes precedence over per-server vars.
Confirm the tools install, audit, outdated, list and run appear in the client's tool list, then ask the agent to run npm list — a structured JSON dependency listing proves the connection works.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
Pare npm is an MCP server from the Pare project that provides structured, typed JSON output for npm/pnpm operations. It wraps common commands like install, audit, outdated, list, and run, converting raw terminal text into schema-validated JSON to avoid brittle string parsing. The server returns two outputs: content (human-readable text) and structuredContent (type-safe JSON) for agents to process directly. It reduces token consumption and improves reliability.
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 57e1980e8375 Data synced 2026-10-13 Read the FMRS scoring method