Featured

Deploy OpenClaw in 60 seconds β€” 20% off logoDeploy OpenClaw in 60 seconds β€” 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger β†’
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger β†’
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free β†’
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now β†’
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data β€” no proxies, no parsers, no maintenance.

Start building free β†’
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it β€” secured from day one.

Get it set up for you β†’
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free β†’
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here β†’

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

mcp-server MCP server](https://glama.ai/mcp/servers/keepgoing-dev/mcp-server/badges/score.svg)](https://glama.ai/mcp/servers/keepgoing-dev/mcp-server) πŸ“‡ 🏠 🍎 πŸͺŸ 🐧 - Project memory for AI coding sessions.

README.md

@keepgoingdev/mcp-server

MCP server for KeepGoing.dev - a momentum companion for developers. KeepGoing helps you keep going on projects when you return after time away.

KeepGoing auto-captures checkpoints (what you were doing, what's next, which files matter) on git commits, branch switches, and inactivity. When you start a new session, your AI assistant reads your last checkpoint instead of re-inferring everything from scratch. Local-first, no account required.

Quick Setup

The easiest way to get started is with the installer, which installs the CLI globally and runs the setup wizard:

curl -fsSL https://keepgoing.dev/install.sh | bash

For a specific tool:

curl -fsSL https://keepgoing.dev/install.sh | bash -s -- claude
curl -fsSL https://keepgoing.dev/install.sh | bash -s -- vscode

Claude Code (manual)

Global (recommended) β€” works across all your projects:

claude mcp add keepgoing --scope user -- npx -y @keepgoingdev/mcp-server

Per-project β€” scoped to a single project:

claude mcp add keepgoing --scope project -- npx -y @keepgoingdev/mcp-server

Then run keepgoing setup claude to configure hooks and rules.

Cursor, Windsurf, and other tools

Add to your MCP config file (~/.cursor/mcp.json for Cursor, or the equivalent for your tool):

{
  "mcpServers": {
    "keepgoing": {
      "command": "npx",
      "args": ["-y", "@keepgoingdev/mcp-server"]
    }
  }
}

Tools

Core

| Tool | Description | |------|-------------| | get_momentum | Get your last checkpoint, next step, blockers, and branch context. Quick snapshot of where you left off. Accepts optional tier and model params for token-aware output. | | get_reentry_briefing | Get a synthesized re-entry briefing with focus, recent activity, and suggested next steps. Accepts optional tier and model params for token-aware briefing tiers. | | get_session_history | Get recent session checkpoints in chronological order. Supports branch filtering and configurable limit. | | get_whats_hot | See recently active files and branches across sessions. | | continue_on | Export your development context as a formatted prompt for another AI tool (chatgpt, gemini, copilot, claude, general). | | save_checkpoint | Save a development checkpoint after completing a task or meaningful piece of work. |

Paid Add-ons

| Tool | Add-on | Description | |------|--------|-------------| | get_decisions | Decision Detection | Get recent high-signal commits with their category, confidence, and rationale. | | get_current_task | Session Awareness | Get current live session tasks across multiple concurrent AI agent sessions. | | activate_license | | Activate a KeepGoing license on this device. | | deactivate_license | | Deactivate the KeepGoing license on this device. |

How It Works

  1. Add this MCP server to your AI coding assistant (Claude Code, Cursor, Windsurf, etc.)
  2. Start coding. Use save_checkpoint from your AI assistant to capture what you did, what's next, and any blockers
  3. Come back anytime. Your AI assistant calls get_momentum or get_reentry_briefing to pick up exactly where you left off
  4. Optionally, install the KeepGoing VS Code extension for automatic checkpoint capture on inactivity, git commits, and branch switches β€” no manual saves needed

All data is stored locally in a .keepgoing/ directory at your git root.

Requirements

  • Node.js 18+
  • The KeepGoing VS Code extension is optional β€” useful for auto-capturing checkpoints on git commits, branch switches, and inactivity, but the MCP server works standalone via save_checkpoint

Links

License

MIT

See related servers & alternatives β†’

Related MCP servers

Browse all β†’

Related guides

Hand-picked reading to help you choose and use Vector & Memory servers.