MCP Memory Gateway MCP Server

1

Add it to Claude Code

Run this in a terminal.

Run in terminal
claude mcp add mcp-memory-gateway -- npx -y mcp-memory-gateway serve
README.md

Persistent memory management and pre-action gates for AI coding agents.

MCP Memory Gateway

Pre-action gates that physically block AI coding agents from repeating known mistakes. Dual-memory recall (MemAlign-inspired principles + episodic context). Captures feedback, auto-promotes failures into prevention rules, and enforces them via PreToolUse hooks. Works with Claude Code, Codex, Gemini, Amp, Cursor.

Honest disclaimer: This is a context injection system, not RLHF. LLM weights are not updated by thumbs-up/down signals. What actually happens: feedback is validated, promoted to searchable memory, and recalled at session start so agents have project history they'd otherwise lose. That's genuinely valuable — but it's context engineering, not reinforcement learning.

Works with any MCP-compatible agent: Claude, Codex, Gemini, Amp, Cursor, OpenCode.

Verification evidence for shipped features lives in docs/VERIFICATION_EVIDENCE.md.

Repo-local operator guides:

MCP Memory Gateway keeps one sharp agent on task. Continuity tools help you resume work. The resumed session stays sharper with recall, reliability rules, pre-action gates, session handoff primers, and verification layered on top of that continuity workflow without another planner or swarm.

Claude Workflow Hardening

If you are selling or deploying Claude-first delivery, the cleanest commercial wedge is not "AI employee" hype. It is a Workflow Hardening Sprint for one workflow with enough memory, gates, and proof to ship safely.

Use that motion when a buyer already has:

  • one workflow owner
  • one repeated failure pattern or rollout blocker
  • one buyer who needs proof before broader rollout

That maps cleanly to three offers:

  • Workflow Hardening Sprint for one production workflow with business value
  • code modernization guardrails for long-running migration and refactor sessions
  • hosted Pro at $49 one-time when the team only needs synced memory, gates, and usage analytics

Use these assets in sales and partner conversations:

Claude Desktop Extensions

This repo already ships a Claude Desktop extension lane:

  • Claude metadata: .claude-plugin/plugin.json
  • Claude marketplace metadata: .claude-plugin/marketplace.json
  • Claude extension install and support guide: .claude-plugin/README.md
  • Claude Desktop bundle builder: npm run build:claude-mcpb
  • Claude Desktop bundle launcher: .claude-plugin/bundle/server/index.js
  • Claude Desktop bundle icon: .claude-plugin/bundle/icon.png
  • Internal submission packet: docs/CLAUDE_DESKTOP_EXTENSION.md

Install locally today with:

claude mcp add rlhf -- npx -y mcp-memory-gateway serve

Build a submission-ready .mcpb locally with:

npm run build:claude-mcpb

Treat Anthropic directory inclusion as a discoverability and trust lane, not as revenue proof or partner proof.

For paired phone + desktop workflows, keep Dispatch in a constrained remote-ops lane:

RLHF_MCP_PROFILE=dispatch claude mcp add rlhf -- npx -y mcp-memory-gateway serve
npx mcp-memory-gateway dispatch

That profile stays read-only: metrics, gates, diagnostics, planning, and recall. Use a dedicated worktree plus RLHF_MCP_PROFILE=default when the task graduates into code edits or memory writes. Guide: docs/guides/dispatch-ops.md.

Cursor Marketplace

This repo now ships a submission-ready Cursor plugin bundle:

  • Root marketplace manifest: .cursor-plugin/marketplace.json
  • Plugin direc

Environment Variables

RLHF_MCP_PROFILESets the operational profile for the gateway (e.g., 'dispatch' or 'default')

Configuration

claude_desktop_config.json
{"mcpServers": {"rlhf": {"command": "npx", "args": ["-y", "mcp-memory-gateway", "serve"]}}}

Try it

Recall the prevention rules established in our last session regarding the database migration.
Capture this feedback about the failed API integration and promote it to a prevention rule.
Retrieve the project history and context for the current refactoring task.
Check the pre-action gates before executing the new deployment script.

Frequently Asked Questions

What are the key features of MCP Memory Gateway?

Persistent memory storage for cross-session context retrieval. Pre-action gates to prevent AI agents from repeating known mistakes. Dual-memory recall using MemAlign-inspired principles. Feedback capture and auto-promotion to prevention rules. Support for Claude, Codex, Gemini, Amp, and Cursor.

What can I use MCP Memory Gateway for?

Maintaining project history and context across multiple coding sessions. Enforcing reliability rules and guardrails during long-running refactors. Preventing recurring bugs by promoting past failures into active prevention rules. Managing workflow handoffs between different AI agent sessions.

How do I install MCP Memory Gateway?

Install MCP Memory Gateway by running: claude mcp add rlhf -- npx -y mcp-memory-gateway serve

What MCP clients work with MCP Memory Gateway?

MCP Memory Gateway works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep MCP Memory Gateway docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare