Best for
- Projects using TypeScript, esbuild, Vite, or webpack
- Developers wanting reliable build diagnostics for agents
- Use cases needing minimal token overhead from build logs
This server provides structured diagnostics from common frontend build tools to AI agents as JSON, reducing parsing overhead. It is non-official and maintained by Dave-London. Specific tools are not listed due to insufficient info, but overall description is clear.
Strongest · Setup experience 12/20 Weakest · Reliability 7/20
Static review · not runListed 2026-08-07
Read the FMRS scoring method →Runtime:Node.js >=20
PARE_TOOLS
Universal tool filter in server:tool,... format limiting tools registered across all Pare servers.
PARE_GIT_TOOLS
Per-server tool filter for the git server, e.g. status,log,diff.
PARE_NPM_TOOLS
Per-server tool filter for the npm server, e.g. install,test,run.
MCP_TIMEOUT
MCP connection timeout in milliseconds for Claude Code, e.g. 30000, to fix connection timeouts.
Configure this server in an MCP client to run the npm package @paretools/build using npx. Example config (if JSON config supported): use "command": "npx", "args": ["-y", "@paretools/build"].
After restarting the client, check that tools from the Pare build server (tsc/esbuild/vite/webpack related) appear in the tool list, or run `npx @paretools/init doctor` to validate the connection.
Once connected, you can ask your AI assistant things like:
Pare Build is one of the Pare MCP servers, focused on build tools. It transforms output from tsc, esbuild, vite, and webpack into typed JSON diagnostics, allowing AI agents to directly use structured data without parsing fragile terminal text. The server runs over stdio and is available as an npm package.
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 2026-10-11 Read the FMRS scoring method