Skip to main content
MCP server CX Codex

MELRA — Claude Code MCP server: what it does, how to install

A local execution layer that checks agent tool calls against policies and records verified receipts.

Install into Claude Code · Platform CLI All methods and platforms ↓
claude mcp add melra -- npx -y @melra/cli
Open on GitHub

What MELRA does

MELRA supervises agent actions by validating every tool call before dispatch. It prompts for manual approval when a requested operation demands confirmation. State-changing mutations execute at most once per task. If an outcome is uncertain, the runtime parks the action for manual review instead of triggering a replay.

Running the tool requires Node.js 22.13+ or 23.4+. The initial setup command establishes an explicit workspace boundary for files and shell operations. Keep in mind that protection covers routed calls only. Any command executed outside the MELRA layer bypasses its policy engine completely.

What it helps with

  • enforce permission policies before agent tool execution
  • prevent duplicate mutations during ambiguous failures
  • restrict agent filesystem access to a target project directory
  • record sanitized audit receipts of completed agent actions

Example prompts for the agent

  • Run database updates via MELRA and ask for approval on destructive actions
  • Execute the build command inside the restricted workspace boundary

How to install MELRA

Platform CLI

claude mcp add melra -- npx -y @melra/cli

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about MELRA

How to install MELRA in Claude Code?

Run claude mcp add melra -- npx -y @melra/cli in your project terminal. Make sure you have Node.js 22.13+ or 23.4+ installed.

What does MELRA do?

It acts as a governance gateway for agent tool calls, checking them against policies and storing redacted receipts. It also prevents duplicate mutation reruns when an operation ends in an ambiguous state.

Does MELRA monitor every action on the machine?

No. MELRA governs only tool calls explicitly routed through its runtime. Actions performed via other tools remain outside its scope.

Similar MCP servers

All MCP servers for Agent setup: memory, context, orchestration →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor