Best for
- Developers using Deno as their runtime who want reliable structured output for AI agents.
- Agent integrations that need to reduce token usage and avoid parsing terminal text.
The Pare Deno server focuses on structured output for Deno runtime operations, providing typed JSON via MCP to reduce token consumption and avoid text parsing issues. It wraps only the Deno tool, making it suitable for agent scenarios that require reliable data sets.
Strongest · Maintenance 14/20 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 server:tool pairs (e.g. 'git:status,npm:install'); takes precedence over per-server filters.
MCP_TIMEOUT
MCP connection timeout in milliseconds for Claude Code; set to 30000 if you hit connection timeouts.
Install the @paretools/deno package via npm and configure it in your MCP client with stdio transport. For example, in Claude Desktop's config, add something like "command": "npx", "args": ["-y", "@paretools/deno"].
After starting the client, confirm the tools registered by the Pare deno server (@paretools/deno, stdio transport) appear in the tool list; you can also run npx @paretools/init doctor to validate, then ask the agent to run a Deno command and check the reply is structured JSON rather than raw terminal text.
Once connected, you can ask your AI assistant things like:
Listed from the project's documentation, not tested by this site.
Pare Deno is an MCP server from the Pare toolkit that wraps the Deno CLI to return structured, schema-validated JSON instead of raw terminal text. This provides AI agents with predictable, typed data they can act on directly, avoiding fragile text parsing. The server is distributed via the npm package @paretools/deno, uses stdio transport, and conforms to the Model Context Protocol.
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 2026-10-12 Read the FMRS scoring method