Rosetta

An instruction layer for AI coding agent

LLM Mart 0 views 4 listing impressions
Transport
Not stated
Package
—
Registry id
—

No install snippet on purpose. A working MCP config is a command, its arguments and an environment block — the last two are where API keys live, so this catalogue never stores them and cannot publish them. Follow the link above for the authors' own instructions.

Rosetta provides engineering governance and context for AI coding agents. Rosetta works across multiple IDEs and coding tools including Cursor, Claude Code, VS Code, JetBrains, Codex, and Windsurf. It merges three layers of instructions at runtime for team customization without forking.

Rosetta can reduce the time for a typical coding task from roughly 75 minutes to 25 minutes. Its guardrails require the agent to assess risk, mask sensitive data, detect dangerous operations, and follow behavior boundaries. Rosetta workflows define human-in-the-loop approval gates after specs, plans, and before risky actions.

It auto-classifies each request into one of thirteen workflow types such as coding, security review, or testing.

Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.

Related servers

PostgreSQL Official

Let an agent inspect a Postgres schema and run read-only queries.

stdio @modelcontextprotocol/server-postgres
26 views

Korean apartment data: 45,000+ complexes, official prices, jeonse ratios, AI forecasts.

25 views
Filesystem Official

Give an agent scoped read and write access to directories you choose.

stdio @modelcontextprotocol/server-filesystem
24 views

Test management over MCP: author cases, run manual executions, cut releases, read health

23 views