Tired of re-explaining your codebase to AI every single time?

ContextStream gives your AI persistent memory that follows you everywhere. Decisions remembered. Context preserved. No more repeating yourself.

Website: contextstream.io | Docs: contextstream.io/docs/mcp

• Close a chat with Cursor → Open a new one → AI forgot everything
• Switch from Claude to Windsurf → Start explaining from scratch
• New team member joins → Days of onboarding conversations
• "Why did we build it this way?" → No one remembers

ContextStream is a universal memory layer for AI coding tools. It works with Cursor, Claude Code, Windsurf, VS Code, and any MCP-compatible client.

You: "Initialize session and remember we use PostgreSQL with TypeScript strict mode"
...later, in a NEW conversation...
You: "What are my preferences for this project?"
AI: "You prefer TypeScript with strict mode, and you're using PostgreSQL."

It remembers. Across sessions. Across tools. Forever.

Sign up at contextstream.io → Settings → API Keys → Create one.

Cursor / Claude Code / Windsurf / VS Code:

{
  "mcpServers": {
    "contextstream": {
      "command": "npx",
      "args": ["-y", "@contextstream/mcp-server"],
      "env": {
        "CONTEXTSTREAM_API_URL": "https://api.contextstream.io",
        "CONTEXTSTREAM_API_KEY": "your_api_key"
      }
    }
  }
}

Codex CLI: Add to ~/.codex/config.toml:

[mcpServers.contextstream]
command = "npx"
args = ["-y", "@contextstream/mcp-server"]
[mcpServers.contextstream.env]
CONTEXTSTREAM_API_URL = "https://api.contextstream.io"
CONTEXTSTREAM_API_KEY = "your_api_key"

Start a chat and say:

"Initialize session and remember that I prefer TypeScript with strict mode"

Then start a brand new conversation and ask:

"What are my preferences?"

✨ It remembers.

ContextStream isn't just memory storage. It understands your code.

"What breaks if I change the UserService class?"

See all dependencies and side effects before refactoring.

"Why did we choose PostgreSQL over MongoDB?"

Recall past decisions with full context and reasoning.

"Find where we handle rate limiting"

Search by meaning, not just keywords. Find code by intent.

"Show dependencies for the auth module"

Visualize connections between code, decisions, and docs.

See all 60+ tools →

Context loads automatically on the first tool call. No manual setup required.

═══════════════════════════════════════════
🧠 AUTO-CONTEXT LOADED (ContextStream)
═══════════════════════════════════════════
📁 Workspace: my-project
📂 Project: backend-api
📋 Recent Decisions:
• Use PostgreSQL for persistence
• JWT for authentication
🧠 Recent Context:
• [decision] API design patterns
• [preference] TypeScript strict mode
═══════════════════════════════════════════

Works with all MCP clients — no client-side changes required.

• Encrypted at rest — All data encrypted with AES-256
• No training on your data — We never use your code to train AI
• You control access — Workspace permissions & API keys
• Self-host option — Enterprise can self-host for full control

• Website: contextstream.io
• Documentation: contextstream.io/docs
• MCP Setup Guide: contextstream.io/docs/mcp
• npm: @contextstream/mcp-server

MIT