Which integrations are available for this server?

Referenced in decision history examples, showing how ContextStream tracks database technology selection rationale and architectural trade-offs. Used as an example database preference in the memory system, demonstrating how ContextStream can remember and recall database technology choices and architectural decisions. Featured prominently in memory examples, demonstrating how ContextStream remembers language preferences, strict mode settings, and coding standards across sessions.

How do I use ContextStream MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ContextStream MCP Server what did we decide about the authentication flow yesterday?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

ContextStream MCP Server by contextstream

npx @contextstream/mcp-server@latest setup

This Isn't Just Memory. This Is Intelligence.

Other tools give your AI a notepad. ContextStream gives it a brain.

Your AI doesn't just remember things—it understands your entire codebase, learns from every conversation, pulls knowledge from your team's GitHub, Slack, and Notion, and delivers exactly the right context at exactly the right moment.

One setup. Instant transformation.

What Changes When You Install This

Before	After
AI searches files one-by-one, burning tokens	Semantic search finds code by meaning in milliseconds
Context lost when conversations get long	Smart compression preserves what matters before compaction
Team knowledge scattered across tools	Unified intelligence from GitHub, Slack, Notion—automatically
Same mistakes repeated across sessions	Lessons system ensures your AI learns from every failure
Generic responses, no project awareness	Deep context about your architecture, decisions, patterns

The Power Under the Hood

Semantic Code Intelligence

Ask "where do we handle authentication?" and get the answer instantly. No grep chains. No reading 10 files. Your AI understands your code at a conceptual level.

SmartRouter Context Delivery

Every message is analyzed. Risky refactor? Relevant lessons surface automatically. Making a decision? Your AI knows to capture it. The right context, every time, without you asking.

Team Knowledge Fusion

Connect GitHub, Slack, and Notion. Discussions from months ago? Surfaced when relevant. That architecture decision buried in a PR comment? Your AI knows about it.

Code Graph Analysis

"What depends on UserService?" "What's the impact of changing this function?" Your AI sees the connections across your entire codebase.

Context Pressure Awareness

Long conversation? ContextStream tracks token usage, auto-saves critical state, and ensures nothing important is lost when context compacts.

Setup Takes 30 Seconds

npx @contextstream/mcp-server@latest setup

The wizard handles everything: authentication, configuration, editor integration, and optional hooks that supercharge your workflow.

Works with: Claude Code • Cursor • VS Code • Claude Desktop • Codex CLI • Antigravity

The Tools Your AI Gets

init → Loads your workspace context instantly context → Delivers relevant context every single message search → Semantic, hybrid, keyword—find anything by meaning session → Captures decisions, preferences, lessons automatically memory → Builds a knowledge graph of your project graph → Maps dependencies and analyzes impact project → Indexes your codebase for semantic understanding media → Index and search video, audio, images (great for Remotion) integration → Queries GitHub, Slack, Notion directly

Your AI uses these automatically. You just code.

Manual Configuration

Skip this if you ran the setup wizard.

claude mcp add contextstream -- npx @contextstream/mcp-server claude mcp update contextstream -e CONTEXTSTREAM_API_KEY=your_key

{ "mcpServers": { "contextstream": { "command": "npx", "args": ["-y", "@contextstream/mcp-server"], "env": { "CONTEXTSTREAM_API_KEY": "your_key" } } } }

Locations: ~/.cursor/mcp.json • ~/Library/Application Support/Claude/claude_desktop_config.json

{ "servers": { "contextstream": { "type": "stdio", "command": "npx", "args": ["-y", "@contextstream/mcp-server"], "env": { "CONTEXTSTREAM_API_KEY": "your_key" } } } }

Use the Copilot CLI to interactively add the MCP server:

/mcp add

Or add to ~/.copilot/mcp-config.json:

{ "mcpServers": { "contextstream": { "command": "npx", "args": ["-y", "@contextstream/mcp-server"], "env": { "CONTEXTSTREAM_API_KEY": "your_key" } } } }

For more information, see the GitHub Copilot CLI documentation.