Brain Os
未认领Local-first MCP memory server for operational project state: decisions, blockers, plans, patterns, and next moves.
安装
npx brain-os init更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
22 个工具中显示 22 个
文档中列出的工具 (22)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
action_guard
Apply built-in guard templates to common high-risk actions before proceeding
audit_log
Read the full mutation history — what changed, when, by whom
context_resolve
Resolve which entity the current work belongs to, from explicit mention / alias / files / lexical signals. Deterministic and confidence-scored — routes known context, never guesses intent.
decision_check
Check a proposed action against active decisions — returns clear/caution/conflict
decision_log
Log a strategic decision with reasoning and alternatives
decision_refresh
Refresh an existing decision: bump reviewdate, append evidence, change status. Metadata only — does not mutate decision content.
decision_review
Review-debt inbox: buckets overdue decisions (still-true / changed / archive / needs-evidence) and recommends an action for each. Read-only — proposes, you confirm. Auto-detects duplicate-stub decisions.
entity_read
Read operational state of one or all tracked entities
entity_update
Update entity state — status, momentum, blockers, next moves
focus_get
Get prioritized recommendations on what to work on
memory_check
Audit memory quality — flags stale data, contradictions, noise
memory_commit
End-of-session commit — save all state changes
pattern_detect
Analyze patterns across all entities
plan_add
Add steps to an existing plan
plan_advance
Complete or skip a step (requires evidence/reason) — auto-promotes next
plan_read
View plan progress and current step
plan_set
Set an ordered plan for an entity — step 1 becomes active nextmove
project_evidence_scan
Read-only scan of a repo's native operating state (STATE.md, FLAGS, HANDOFF, ROADMAP/PLAN/TODO, git activity, dirty files) for human gates, next moves, and do-not-touch — grounds focus in repo reality.
risk_assess
Classify risky actions before execution, including public-release and destructive-operation risks
semantic_recall
Search memory by meaning using natural language
wrap_auto
Non-interactive safety-net wrap: applies low-risk fields and stages high-risk changes for review
wrap_check
Detect whether meaningful state changes have accumulated since the last wrap