MemScope
為團隊的 AI 代理提供受治理的共享記憶:由人員設定誰可以讀取每則記憶,管理員也無法繞過,並提供稽核記錄。
託管 MCP 伺服器
npx add-mcp 'https://mcp.memscope.ai/mcp'可安裝到 Claude Code、Codex、Cursor 等客戶端
文件
Your coding agents either forget everything or share too much.
Works with Claude Code, Cursor and ChatGPT.
MemScope gives your team one shared memory. Each person’s agent gets back only what that person is allowed to see. Your rules decide, never AI.
No credit card. 10,000 memories/month. Connect in minutes via MCP.
Example: one company, 13 memories, different answers
The home page shows one example company with 13 shared memories in a single store. Choose who is asking, and the files that person's AI can recall light up; the rest stay dark, and their words are never sent. Acme's policy decides, never AI.
- Dana (Engineering · Falcon): 8 of 13.
- Omar (Sales): 5 of 13.
- Avery (Admin): 6 of 13. Being an admin adds nothing: there is no admin bypass.
- MemScope staff: none of the content. Every record reads XXX, unless the customer grants time-limited, audited support access.
AI knowledge silos are either useless or dangerous
Every assistant learns something useful, then it disappears inside a single conversation. Share everything and HR knowledge leaks into Engineering. Share nothing and the organization learns no faster than one person can type.
- HR. Compensation, reviews and hiring notes should never surface in Engineering chats.
- Legal. Privileged and contract knowledge stays inside the boundary.
- Executive. Board and strategy context is restricted by default.
- Projects. Project Falcon knowledge belongs to Project Falcon members only.
- Personal. Personal memories stay with the person who saved them until they choose to share.
Every memory says who can see it and how sensitive it is
When AI labeling is on, a fast AI model suggests sensitivity, topic and tags. Who can see a memory is decided by your organization’s policy, never by AI — and the same memory and person always get the same answer.
- Who can see it. Shared (everyone), a team, a project, or Personal (only the author).
- Sensitivity. Public → Internal → Restricted → Highly restricted. Higher levels need more access.
- Topic. HR, Legal, Executive, Engineering… sensitive topics go only to the team you choose.
Admins manage. They don’t read.
Organization Owners and Admins manage people, teams and policy — but there is no administrative bypass in the authorization engine. Platform staff see XXX for memory content unless a customer issues a time-limited, audited support grant.
- AI never grants access. AI only suggests labels.
- No admin bypass. Owner/Admin ≠ data reader. Ever.
- Staff see XXX. Content redacted by default.
- Audited support grants. 1h / 24h / 7d, revocable, logged.
Works with the AI you already use
One MCP endpoint and a plain REST API. Your agents keep their workflow; MemScope governs the memory.
- Claude Code
- Cursor
- OpenAI Codex CLI
- ChatGPT
- GitHub Copilot in VS Code
- Gemini CLI
- Windsurf
- Claude Desktop and claude.ai
Give your AI a memory worth trusting
Start a free 60-day trial and connect your first client in minutes. Pricing.
Web page: https://memscope.ai/ · All facts for AI agents: https://memscope.ai/llms.txt