Every AI coding session starts by re-explaining context the last session already knew. `.brain` is a folder in your repo that Claude Code, Cursor
Every AI coding session starts by re-explaining context the last session already knew. .brain is a folder in your repo that Claude Code, Cursor, and Codex all read via one MCP server. Decisions, policies, plans — written once, remembered. The nucleus mcp mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 13 defined tools rather than through you.
Everything the assistant can do here goes through one of these:
GROUND — Execution verification (5 tiers: diff, syntax, imports, tests, runtime)ALIGN — Human corrections (verdict + delta + DPO + event in one call)Memory — Engrams that persist across sessions. Write once, recall foreverSessions — Save context, resume later. Session arc shows your last 3 sessionsTasks — Priority queue with escalation, HITL gates, and heartbeat monitoringGovernance — Kill switch, compliance configs (EU DORA, MAS TRM, SOC2), audit trailsOrchestration — Agent slots, multi-brain sync, task dispatchArchive — Training pipeline (SFT + DPO), delta tracking, frontier health dashboardJurisdiction — Retentioneu-dora — 7 yearssg-mas-trm — 5 yearsus-soc2 — 1 yearInstallation goes through your MCP client rather than a global install: point it at nucleus-mcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
You will need one environment variable: NUCLEUS_BRAIN_PATH. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Nucleus MCP's toolset — GROUND, ALIGN, Memory and 10 more — is a fair guide to whether it matches your workflow. It is maintained by eidetic-works; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| GROUND | Execution verification (5 tiers: diff, syntax, imports, tests, runtime) |
| ALIGN | Human corrections (verdict + delta + DPO + event in one call) |
| Memory | Engrams that persist across sessions. Write once, recall forever. |
| Sessions | Save context, resume later. Session arc shows your last 3 sessions. |
| Tasks | Priority queue with escalation, HITL gates, and heartbeat monitoring. |
| Governance | Kill switch, compliance configs (EU DORA, MAS TRM, SOC2), audit trails. |
| Orchestration | Agent slots, multi-brain sync, task dispatch. |
| Archive | Training pipeline (SFT + DPO), delta tracking, frontier health dashboard. |
| Jurisdiction | Retention |
| eu-dora | 7 years |
| sg-mas-trm | 5 years |
| us-soc2 | 1 year |
| global-default | 90 days |
Claude Code `.mcp.json` snippet:
```json
{
"mcpServers": {
"nucleus-rabbithole": {
"command": "nucleus-rabbithole",
"args": []
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| NUCLEUS_BRAIN_PATH | Filesystem location the server is allowed to use. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.