Mmcp.market

Piia Engram MCP server

by Patdolitse·io.github.Patdolitse/piia-engram·v4.20.0

Local-first AI identity for MCP coding tools. Lessons, decisions, and context you control.

A92/100grade A
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

160 stars

Reviews

Write one

Nobody has reviewed Piia Engram yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Piia Engram tools (60, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • _session_handoff_state

    Extract only explicit completion/next/blocking signals for a checkpoint.

  • add_decision

    记录单条关键决策(用户明确选了某个方案)。 / Record one key decision when the user explicitly chose an option.

  • add_lesson

    记录单条经验教训(你已经知道要记什么)。 / Record one lesson learned when you already know what to save.

  • add_playbook

    记录操作手册(Playbook)— 结构化的多步骤流程。 / Record an operational playbook — a structured multi-step procedure.

  • archive_knowledge

    按 ID 归档 lesson 或 decision(自动识别类型)。 / Archive a lesson or decision by ID, automatically detecting the item type.

  • check_anchors

    Owner-only: revalidate anchor-backed freshness provenance for one repository.

  • confirm_knowledge

    Owner-only: explicitly stamp a knowledge item with human/test/anchor freshness provenance.

  • doctor

    记忆系统自诊断。 / Memory system self-diagnosis.

  • explore_knowledge

    探索知识关联:相连条目、相似条目或全库合并建议。 / Explore knowledge links: related items, similar items, or merge candidates across the library.

  • export_engram

    导出 Engram 数据:单文件备份或 OpenClaw 兼容格式。 / Export Engram data: a single-file backup, or the OpenClaw-compatible format.

  • export_feedback_report

    导出匿名内测反馈报告。 / Export anonymous beta feedback report.

  • export_knowledge_report

    导出完整 Markdown 知识报告并返回内容。 / Export a full Markdown knowledge report and return its content.

  • extract_session_insights

    从会话摘要中批量自动提取经验教训和决策(你不需要自己分类)。 / Automatically extract lessons and decisions from a session summary without manually classifying them.

  • find_tool

    搜索已注册的本地工具/程序。 / Search for registered local tools and programs.

  • get_audit_log

    获取最近的审计日志条目。 / Get recent audit log entries.

  • get_daily_log

    读取项目的每日日志(人类可读的会话时间线)。 / Read a project's daily log (human-readable session timeline).

  • get_decisions

    按时间列出关键决策;也可还原决策链或某个问题的修订历史。 / List the user's key decisions by time; can also reconstruct a decision thread or a question's revision history.

  • get_identity_card

    导出用户的可携带 AI 身份卡(Markdown 格式)。 / Export the user's portable AI identity card as Markdown.

  • get_identity_facets

    按切面读取用户身份信息(画像/偏好/信任边界/工作风格/质量标准/领域图谱)。 / Read user identity facets: profile, preferences, trust boundaries, work style, quality standards, and the domain map.

  • get_knowledge_history

    查看一个知识条目(lesson/decision/playbook)的修订历史。 / Return the revision history (superseded snapshots) of one knowledge item.

  • get_knowledge_inheritance

    为新项目或任务生成可继承知识包。 / Build a knowledge inheritance pack for a new project or task.

  • get_knowledge_overview

    获取统一的知识概览:摘要、健康报告和过期知识。 / Get a unified knowledge overview: digest, health report, and stale items.

  • get_lessons

    获取用户从过去项目中学到的经验教训。 / Get lessons the user learned from past projects.

  • get_permission_profile

    查看当前所有调用者的权限全景:谁有什么信任级别、能看到什么。 / View the permission landscape: who has what trust level and what they can access.

  • get_playbooks

    Playbook 统一读取入口:列表 / 单条 / 最近使用 / 管理视图。 / Unified Playbook reader: list, single item, recently used, or management view.

  • get_project_context

    读取特定项目的知识快照(项目级,只含该项目的历史)。 / Read the knowledge snapshot for a specific project, containing only that project's history.

  • get_recall

    获取结构化 Recall Surface v1 载荷。 / Get a structured Recall Surface v1 payload.

  • get_recent_context

    找回最近的 AI 对话上下文。 / Retrieve the most recent AI conversation context.

  • get_relevant_knowledge

    按项目路径自动推荐最相关的经验教训(无需搜索词)。 / Automatically recommend the most relevant lessons for a project path, without search keywords.

  • get_resume_brief

    跨会话/跨工具接续简报(v3.30 新增)。 / Cross-session, cross-tool resume brief.

  • get_stale_knowledge

    列出超过指定天数未复习的知识条目。 / List knowledge items not reviewed for more than the specified number of days.

  • get_user_context

    获取用户的个性化上下文(冷启动,分层延迟可控)。 / Get tiered cold-start user context with latency control.

  • get_wrap_up_session_status

    读取 wrap_up_session 的阶段状态。 / Read metadata-only stage status for a wrap_up_session operation.

  • import_engram

    导入 Engram 数据:从备份文件或 OpenClaw 兼容文件。 / Import Engram data: from a backup file, or from OpenClaw-compatible files.

  • ingest_notes

    从自由文本笔记中提取经验教训和关键决策并写入知识库。 / Extract lessons and key decisions from free-form notes and save them to the knowledge base.

  • list_agent_sessions

    列出可用的 AI 对话上下文记录(仅元数据)。 / List available AI context sessions (metadata only).

  • list_projects

    列出用户参与过的所有项目及基本信息。 / List all projects the user has worked on with basic metadata.

  • list_tools

    列出所有已注册的本地工具/程序。 / List all registered local tools and programs.

  • manage_caller_trust

    调用者信任统一入口:授予 / 修改 / 撤销某个 AI 工具的信任级别。 / Unified caller-trust management: grant, change, or revoke an AI tool's trust level.

  • manage_playbook

    Playbook 统一管理入口:更新 / 归档 / 删除 / 恢复。 / Unified Playbook management: update, archive, delete, restore.

  • manage_relation

    知识关系统一入口:建立或移除条目间关联(无类型双向 / 有类型有向)。 / Unified knowledge relations: create or remove links between items (untyped bidirectional, or typed directed).

  • memory_store

    统一知识写入入口 — 根据 kind 自动路由到 add_lesson / add_decision / add_playbook。 Unified knowledge write endpoint — routes to add_lesson / add_decision / add_playbook based on kind.

  • merge_knowledge

    将次要知识条目合并进主知识条目。 / Merge a secondary knowledge item into a primary knowledge item.

  • onboard_accept

    Owner-only: accept an onboard candidate and stamp anchor provenance.

  • onboard_repo

    Owner-only: scan a repo and create staging repo-fact candidates.

  • playbook_execution

    Playbook 执行统一入口:准备计划 / 更新步骤 / 查看状态。 / Unified Playbook execution: prepare a plan, update a step, or check status.

  • preview_context_governance

    Build a local context-governance preview; proposal-only, no apply.

  • read_web_content

    读取网页、视频或文章的文本内容。 / Read text content from a web page, video, or article.

  • refresh_quick_context

    刷新本地 `quick_context.md` 快照(跨工具 / 离线场景的快速通路)。 / Refresh the local quick_context.md snapshot (cross-tool / offline fast path).

  • register_tool

    注册本地工具/程序到环境图谱(已存在则更新)。 / Register a local tool or program in the environment registry; updates if it already exists.

  • request_outline_review

    生成交互式知识审查 HTML 页面,用户可在浏览器中逐条保留或归档知识。 / Generate an interactive knowledge review HTML page where the user can retain or archive items.

  • review_staging

    知识评审统一入口:列队列 / 批量审批 / 单条复习 / 执行审查结果。 / Unified knowledge review: list the staging queue, batch-approve, refresh one item, or apply review-page results.

  • save_agent_context

    自动保存 AI 对话上下文检查点。 / Auto-save an AI conversation context checkpoint.

  • save_project_snapshot

    写入或更新项目的知识快照(写操作,不是读取)。 / Write or update a project's knowledge snapshot; this is a write operation, not a read.

  • search_knowledge

    搜索知识库(lessons/decisions/playbooks)。 / Search lessons, decisions, and playbooks by keyword.

  • start_project

    新项目一键启动:继承跨项目经验并建立项目档案。 / Start a new project in one step: inherit cross-project knowledge and create a project record.

  • update_identitywrite action

    更新一个身份字段。 / Update one identity field.

  • update_knowledgewrite action

    按 ID 更新 lesson、decision 或 playbook(自动识别类型)。 / Update a lesson, decision, or playbook by ID, automatically detecting the item type.

  • user_portrait

    用户写照统一入口:查看 / 对比 / 保存快照。 / Unified user portrait: view, compare, or snapshot.

  • wrap_up_session

    会话结束一键收尾:自动提取知识、操作流程并保存项目快照。 / Wrap up a session in one step: extract knowledge, detect playbooks, and save a project snapshot.

Public scan report

scanner v0.1.9 · 2026-09-20 · same rubric, same numbers if you re-run it

no findings
  • Code scan131 source files scanned25/25
  • Live reliabilityno gateway calls yet and no remote to proben/a
  • Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 19 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the Piia Engram repository's README, as published. We do not edit it. Read it on GitHub

<!-- mcp-name: io.github.Patdolitse/piia-engram -->

Piia Engram

Local-first AI work identity you can see, edit, and override — portable across your MCP coding tools.

Tell AI once who you are, how you work, and what "good" means. Claude Code, Codex, Cursor, Windsurf, and other MCP-compatible tools can start from the same AI work identity layer — local files you own, no cloud account, no hidden memory you cannot inspect.

Install · See It in Action · Supported Tools · MCP Tools · FAQ

ENGLISH | 中文

Listed in:

Also listed in: awesome-agents · Awesome-MCP-ZH · mcpservers.org · Cursor Directory · ModelScope · PulseMCP

TL;DR: piia-engram is a local-first personal AI identity layer. It helps multiple coding agents start from the same understanding of you: your preferences, quality bar, lessons learned, decisions, and project context. It is not an agent memory database; it is the user-owned layer above your tools.

Why not just use native memory? Claude Code, Codex, Cursor, and Windsurf are adding their own memories and rules. Those are useful, but they are scoped to one tool or workspace. piia-engram gives you one portable identity layer above them: local files you own, AI-proposed knowledge you review, and context that can follow you across tools.

Trust model in four lines:

  • No cloud account: install with pip, keep the core store on your machine.
  • Local files: identity and knowledge live under ~/.engram/ as JSON/Markdown.
  • User approval: AI writes locally; high-risk items (credentials, shell commands, MCP config, permission rules) wait for your review, while low/medium writes are auto-absorbed but fully auditable and reversible. Set ENGRAM_APPROVAL=strict to gate every write.
  • Documented boundaries: see Trust model, Privacy, and Security.

Want proof? See the live cross-tool continuity proof — a memory written by Claude Code, read back by Codex through one local store — or the one-command reproducible code demo.

See It in Action

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

claude mcp add piia-engram -- uvx piia-engram
Add to Cursor

Piia Engram: common questions

Is Piia Engram MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Piia Engram safety report
How do I install Piia Engram?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Piia Engram need an API key?
No secret keys are declared. It reads 3 settings from the environment.
Is Piia Engram maintained?
The last commit was 19 days ago (2026-09-01). The latest release is v4.20.0.
What can I use instead of Piia Engram?
Servers from other publishers that do the same job: Plur MCP server and Prism Coder MCP server.

Alternatives to Piia Engram

Same job from other publishers: the closest match first, then the best rated.

  • Plur
    Open, local-first engram memory for AI agents: read, correct, delete; shared over MCP.
    A
  • Prism Coder
    Session memory for coding agents: local-first recall, drift detection, on-device inference.
    C

More from Patdolitse