Skip to content
MCP server

MemScope

Shared team memory for coding agents where each person recalls only what they may see

Pricing
Free trial
Platforms
Web, API
Runs
Remotely
Version
0.1.0
Listing updated
2 days ago

About MemScope

MemScope is an MCP server for knowledge and memory. It runs as a hosted remote server, so there is nothing to install locally.

Access in MemScope is decided by your organisation's rules, not by an AI. Each saved memory carries a visibility (everyone, a team, a project or personal), a sensitivity level from public to highly restricted, and a topic such as HR or Legal. A language model can suggest labels when you turn that on, but the same memory and the same person always give the same answer.

The site's own example shows eight of thirteen memories visible to one engineer, with the reason for each. Owners and admins manage people, teams and policy but have no bypass to read content, and platform staff see redacted text unless a customer issues a time-limited, audited support grant of 1 hour, 24 hours or 7 days.

It connects through one MCP endpoint or a REST API and lists Claude Code, Cursor, Codex CLI, ChatGPT, GitHub Copilot in VS Code, Gemini CLI, Windsurf and Claude Desktop. The site says it launches on December 1, 2026, with launch pricing for early adopters.

Install

Run in a terminal

claude mcp add --transport http memscope https://mcp.memscope.ai/mcp

Add to Settings → Connectors → Add custom connector

https://mcp.memscope.ai/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "memscope": {
      "url": "https://mcp.memscope.ai/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "memscope": {
      "type": "http",
      "url": "https://mcp.memscope.ai/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "memscope": {
      "serverUrl": "https://mcp.memscope.ai/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "memscope": {
      "type": "http",
      "url": "https://mcp.memscope.ai/mcp"
    }
  }
}

What it does

Policy-based recall
Each person's agent gets back only memories their organisation's rules allow.
Sensitivity and topic labels
Memories carry visibility, sensitivity and topic, optionally suggested by AI.
No admin bypass
Owners and admins cannot read memory content through their role.
Audited support grants
Staff access is redacted unless a customer issues a revocable, logged grant.
MCP and REST access
One MCP endpoint plus a plain REST API.

Good for

  • Share project decisions across a team's coding agents
  • Keep HR or legal context out of engineering chats
  • Let an agent remember personal preferences privately
  • Audit why an agent could or could not recall something

Pricing

Free trial, from $15 a month

60-day free trial; Team $15 per connected user per month

Prices change. Check memscope.ai before you buy.

MemScope FAQ

How much does it cost?

The Team plan is $15 per connected user per month. A 60-day trial is free, with 3 connected users and 10,000 memories a month, no card needed.

Does AI decide who sees a memory?

No. The site says AI only suggests labels; visibility comes from your policy.

What happens when the trial ends?

Saving new memories stops, while existing ones stay readable and exportable.

Which clients work with it?

Claude Code, Cursor, OpenAI Codex CLI, ChatGPT, GitHub Copilot in VS Code, Gemini CLI, Windsurf and Claude Desktop.

Is MemScope free?

MemScope is a paid product with a free trial. Paid plans start at $15 a month.

How do I add MemScope to Claude Code?

Run this command in your terminal: claude mcp add --transport http memscope https://mcp.memscope.ai/mcp

What are the best alternatives to MemScope?

The closest alternatives to MemScope are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.

Alternatives to MemScope

  1. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  2. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  3. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  4. Local-first long-term memory layer for AI agents, served over MCP

    Not checked yet
    • 5 tools
    • Remote
    • Open source
    • 1.3K GitHub stars
    • Knowledge and memory
  5. note1

    MCP server

    MCP server giving AI assistants search and summaries across your note1 meetings

    • 4 tools
    • Remote
    • Free trial
    • 1 GitHub star
    • Productivity