Melra
Open-source local MCP runtime that checks AI-agent tool calls, gates risky actions on approval, verifies results, and avoids blind retries after timeouts.
{ "mcpServers": { "xagi-lab-melra": { "command": "npx", "args": [ "-y", "@melra/[email protected]" ] } }}.cursor/mcp.jsonMCP server
- Transport
- stdio
- Status
- Local
エージェントを強化
このサーバーを追加
The publisher's own command. Not a PlugMCP endpoint.
キーとログ付きでコピーをホスト。
Local command
npx -y @melra/[email protected]Claude Code has no install link for a local command. Copy the command below and run it in a terminal.
shClaude Code
claude mcp add xagi-lab-melra -- npx -y @melra/cli@0.3.0-alpha.14Run in a terminal.
jsonClaude Desktop
{ "mcpServers": { "xagi-lab-melra": { "command": "npx", "args": [ "-y", "@melra/[email protected]" ] } }}claude_desktop_config.json
Local · npmPublisher installStep-by-step: add this in Claude
Remote URL or a command on your machine? How the two installs differ
PlugMCP で実行
キーとログ付きでコピーをホスト。
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
起動Server facts
Local- Transport
- stdio
- License
- AGPL-3.0
- Last checked
- 2026-11-10
- Stars
- 13
- Tools
- —
- Uptime
- —
Tools
Tools
No tool list yet. Remote servers get one after the first health check.
FAQ
Questions
How do I install Melra?
Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.
Does Melra need an API key?
No required environment variable is listed on this record.
What transport does Melra use?
Melra runs locally over stdio.
When was Melra last checked?
Last checked 2026-11-10. Open-source local MCP runtime that checks AI-agent tool calls, gates risky actions on approval, verifies results, and avoids blind retries after timeouts.
From the publisher
Documentation
README is not crawled yet. Open the repository
Open-source local MCP runtime that checks AI-agent tool calls, gates risky actions on approval, verifies results, and avoids blind retries after timeouts.