[FEATURE] Add cachly MCP server to recommended MCP tools documentation
Preflight Checklist
- [x] I have searched existing requests and this feature hasn't been requested yet
- [x] This is a single feature request (not multiple features)
Problem Statement
Claude Code has no persistent memory between sessions. Every time I open a new
window, my AI assistant has forgotten my architecture, my deployment process,
the bugs I've fixed, and every decision I've made. I have to re-explain context
manually at the start of every session — which takes 5–15 minutes and breaks
the flow of work.
There is already a working MCP-based solution for this (cachly AI Brain), but
it's not discoverable through Claude Code's official documentation.
Proposed Solution
Add cachly (@cachly-dev/mcp-server) to the official MCP server recommendations
or documentation — ideally in the section about memory and context persistence.
The ideal experience:
- User sees cachly listed in Claude Code docs under "Recommended MCP Servers"
- Runs:
npx @cachly-dev/mcp-server@latest setup - Wizard auto-detects Claude Code, writes
~/.claude/mcp.jsonautomatically - Claude Code now has persistent memory: sessions, lessons learned, team brain
The server is free (€0 tier, no credit card), EU-hosted (GDPR), and has
~2,300 weekly installs on npm already.
npm: https://www.npmjs.com/package/@cachly-dev/mcp-server
Docs: https://cachly.dev/docs/ai-memory
Alternative Solutions
Currently users have to manually configure MCP servers without any guidance
on which ones provide memory/persistence. The cachly setup wizard already
handles all of this automatically, but users don't know it exists.
Priority
High - Significant impact on productivity
Feature Category
MCP server integration
Use Case Example
- Developer opens Claude Code on Monday morning
- Without cachly: spends 10 min re-explaining architecture, last week's bugs, deployment process
- With cachly (configured via Claude Code docs recommendation):
- session_start returns: "23 lessons stored, last session: fixed Postgres connection pool bug, deployed API v2.1"
- Developer immediately continues where they left off
- Saves ~45 min/day per developer
Additional Context
_No response_
This issue has 3 comments on GitHub. Read the full discussion on GitHub ↗