MD Feedback

Review your plan. Guide your AI agent. Ship with confidence.

MD Feedback is a VS Code extension that turns markdown plans into structured review annotations (Fix / Question / Highlight). AI agents read your feedback directly through MCP — no copy-paste, no export step, no context lost between sessions.

Install from VS Code Marketplace, open a .md plan, press 1/2/3, and your agent can act on that review immediately.

You review. The agent builds. Gates track completion. Handoffs preserve context.

How It Works

From plan to implementation, the complete AI coding loop:

Step 1  YOU        Write a plan in markdown
          │
Step 2  YOU        Open in MD Feedback sidebar → highlight, fix, question
          │         (press 1, 2, or 3)
          │
Step 3  AGENT      Reads annotations via MCP — no export step needed
          │
Step 4  AGENT      Implements fixes, answers questions
          │
Step 5  AGENT      Marks memos done → gates auto-evaluate
          │         "3 fixes remaining" → "All done, ready to merge"
          │
Step 6  AGENT      Generates handoff → next session picks up where you left off

You do steps 1–2. The agent does the rest.

This is the MCP-first path. If you use export-based workflow, run export after step 2.

Capabilities

3 annotation types: Highlight, Fix, Question
12 MCP tools for agent integration
Export to 11+ AI tools (Claude Code, Cursor, Copilot, Cline, Windsurf, Roo Code, Gemini, Codex, Antigravity, Generic)
Session handoff with checkpoint restore
Quality gates with auto-evaluation

Quick Start (under 2 minutes)

Install from VS Code Marketplace
Connect MCP — add to your AI tool config (Claude Code, Cursor, etc.):

{ "mcpServers": { "md-feedback": { "command": "npx", "args": ["-y", "md-feedback"] } } }

Annotate — open a .md file in the sidebar, press 1 (highlight), 2 (fix), 3 (question)
Done — your agent reads annotations directly via MCP. No export needed.

No MCP? Use Command Palette → MD Feedback: Export → pick your AI tool.

Try it now: Install from Marketplace, open any .md file, and press 2 to add your first Fix annotation.

MCP Server

MD Feedback includes an MCP server that lets AI agents read your annotations without manual export. Agents can query memos, mark tasks done, check gate status, and generate handoffs — all through the Model Context Protocol.

Setup:

npx md-feedback

For full details, see MCP Server documentation.

Packages

Package	Description	Published
apps/vscode	VS Code Extension	Marketplace
apps/mcp-server	MCP Server	npm
packages/shared	Shared types & utils	Private

License

SUL-1.0 — Free for personal and non-commercial use.

FAQ

What is MD Feedback? MD Feedback is a VS Code extension and MCP server for reviewing AI-generated plans before implementation. Select text, press 1 (highlight), 2 (fix), or 3 (question) — annotations are stored as portable HTML comments in the markdown file itself. Export to 11+ AI tools or let agents read directly via MCP.

How is this different from Markdown Preview Enhanced? Markdown Preview Enhanced is a read-only renderer. MD Feedback is an interactive review tool — you annotate plans with structured feedback that AI agents can act on.

Does it work with Claude Code / Cursor / Copilot? Yes. MD Feedback exports to Claude Code (CLAUDE.md), Cursor (.cursor/rules/), GitHub Copilot (.github/copilot-instructions.md), and 8 more tools. With MCP, agents read annotations directly — no export step needed.

What is MCP and why does it matter? MCP (Model Context Protocol) lets AI agents interact with external tools. MD Feedback's MCP server gives agents direct access to your annotations, so they can read feedback, mark tasks done, evaluate gates, and generate handoffs automatically. For example, when you mark a section as "Fix: use retry logic here," the agent reads that annotation via MCP, implements the fix, and marks it done — all without you switching tabs.

Is it free? Yes. MD Feedback is free for personal and non-commercial use under the SUL-1.0 license.

Who is this for? Developers using AI coding assistants (Claude Code, Cursor, Copilot, etc.) who want to review plans before implementation, preserve context across sessions, and give agents structured feedback instead of unstructured chat messages.

md-feedback

Quick Install