Cachly Dev MCP

cachly — experience for coding agents (MCP server)

Solve it once. From then on, your AI knows.

Every fix, every decision and every dead end becomes experience your AI uses at

the right moment. You build faster, and your team builds on what you figured out.

@cachly-dev/mcp-server connects cachly to Claude Code, Cursor, GitHub Copilot, Windsurf, Cline, Continue.dev, Zed, Codex CLI and Gemini CLI over MCP. It offers 124 MCP tools. Your editor lists 27 entries by default and reaches the rest through one of them, cachly_tool (details under MCP Tools below). Your AI stores a lesson after a fix, and finds it again when the same problem returns. Your Brain (the store of your lessons) lives on EU servers.

Start without an account

Claude Code

/plugin marketplace add cachly-dev/cachly-mcp

/plugin install cachly-brain@cachly

There is no JSON to write, no path to set and no key to copy. Without a key, cachly creates a test Brain on EU servers when the session starts (the plugin hook does it; the first tool call does it if the hook did not). The test Brain has 14 days of the Solo tier. After that it runs on the free tier with the same key.

Check it with claude mcp list. You should see plugin:cachly-brain:cachly … ✔ Connected. claude plugin details shows MCP servers (0) even when the server runs, because it does not count them.

The plugin adds three Claude Code hooks:

Turn on auto-update once: /plugin → Marketplaces → cachly → Enable auto-update. Claude Code leaves it off for marketplaces outside Anthropic's own. The MCP server updates itself on every start, but the hooks come with the plugin and update only with it. If an update is waiting, the first session_start of a session says so in one line.

Keep your test Brain

npx @cachly-dev/mcp-server@latest claim

You sign in once in the browser. The test Brain then moves into your account with all its lessons. Every test key is revoked, and you get a new key that is stored where your editor and hooks look for it. The Brain restarts once, which takes about 20 seconds. If you already have a free Brain, the one-Brain limit of the free tier applies and the move is refused with a message.

Cursor, Windsurf, VS Code, Cline, Continue.dev, Zed

npx @cachly-dev/mcp-server@latest autopilot

autopilot finds the editors you use and writes the MCP config for each. It also writes the rule file each editor reads in every chat (CLAUDE.md, AGENTS.md, .cursor/rules/cachly.mdc, .github/copilot-instructions.md, .windsurfrules, .clinerules; GEMINI.md, .junie/guidelines.md and .continue/rules/cachly.md where you use Gemini CLI, Junie or Continue), which tells your AI to check its memory before a task. It adds a git hook that learns from your commits and fills your Brain from your git history. You sign in once in the browser (a device code, no password, no credit card), so the Brain belongs to your own account from the start. Restart your editor afterwards.

You can also add the server by hand (see Manual Setup). Without a key, the first tool call creates the same test Brain as in Claude Code. Without a rule file, Claude Code still starts each task with smart_recall, because the server's instructions ask for it. Gemini CLI also passes them on. Some editors do not (Cline, Continue and Zed, for example); there, the rule file from autopilot is what makes your AI use its memory.

Already inside Claude, Cursor or Copilot? Paste this to your AI:

`

Set up cachly for this project. Run: npx @cachly-dev/mcp-server@latest autopilot

Follow the browser sign-in, then restart the editor.

`

VS Code extension

Install [cachly Brain](https://marketplace.visualstudio.com/items?itemName=cachly-dev.cachly-brain). It creates your Brain on first start, with no account form.

JetBrains plugin

Install [Cachly Brain](https://plugins.jetbrains.com/plugin/32059-cachly-brain) from the JetBrains Marketplace (IntelliJ IDEA, PyCharm, GoLand, WebStorm, Rider). The status bar, the Brain health and the lessons view live in the IDE. The source is at cachly-dev/cachly-intellij. The JetBrains plugin guide shows how Claude Code, Junie and JetBrains AI Assistant get the Brain over MCP.

MCP Registry

The server is listed in the official [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers?search=cachly) as io.github.cachly-dev/mcp-server. Clients that browse the registry find it by name. The entry points at this npm package.

Guides

How it works

1. A fix, a decision or a dead end is stored as a lesson: topic, what worked, what failed, severity, file paths, commands and author.
2. At the start of a session, your AI receives a briefing with the last session, open failures and recent lessons.
3. When you ask for something, smart_recall looks up the lessons that match. It combines keyword search (BM25), meaning-based search and the causal graph, in 11 languages.
4. When an error appears, causal_trace walks from the symptom to the cause and to the fix that worked.
5. Before a deploy, brain_predict lists failure patterns from past incidents.
6. A git hook and the CI templates add lessons from commits and from red-to-green runs.
7. Lessons are shared in the team. Each one carries the name of whoever learned it.

To see what your AI would know before you install anything, run npx @cachly-dev/mcp-server@latest demo in a project folder. It reads your git history and prints your fixes, patterns and decisions. Nothing leaves your machine.

Our agreement with you. You can leave and take your data: npx @cachly-dev/mcp-server@latest export writes every lesson to lessons.md (to read) and lessons.jsonl (to reuse). Code excerpts are stored only if you call index_project yourself, and only on your own EU instance. Read what leaves your machine before you decide.

MCP Tools (124 total, 27 listed by default)

Your editor sees 27 entries by default: the daily tools (26 of them) and one dispatcher, cachly_tool. This is on purpose. The full list of 124 costs about 28,000 tokens in every request. The 27 listed entries cost about 8,000. All other tools (98 of them) run through the dispatcher:

cachly_tool(tool: "team_roster")                  run any of them by name

cachly_tool(tool: "team_roster", describe: true) get its schema first

Nothing is unreachable. The server dispatches by name, so team_roster called directly still works. Set CACHLY_ALLE_WERKZEUGE=1 to list all 124. Set CACHLY_PROFILE=lean to list 8 plus cachly_tool, or CACHLY_PROFILE=recall to list the 3 read-only tools.

Session and lessons (most used)

Team Brain and org knowledge graph

Causal intelligence

| `brain_from_git` | Fill people, file