Setting up
Connect your assistant
One command detects supported assistants, signs you in, and writes the MCP connection and instruction files.
Setup connects both halves of the experience: the MCP capability and the managed instructions that teach your assistant to use it on its own initiative. Afterwards, you can state the outcome instead of coaching every context lookup.
Run the setup
# macOS and Linux
curl -fsSL https://contextstream.io/scripts/mcp.sh | bash
# Windows, in PowerShell
irm https://contextstream.io/scripts/mcp.ps1 | iexIt walks you through the whole thing:
Sign in
Opens a browser. No API key to copy.
Pick a workspace
Join an existing one or create it. This is the boundary your memory lives in — see Workspaces and projects.
Link this project
The folder you ran it in becomes a project. Later folders resolve on their own.
Choose your editors
It detects what you have installed and asks which to connect.
Finish the connection
The setup creates each selected editor's connection and instruction files for you. Where supported, it also enables automatic context guidance.
Index the project
Starts in the background. You can work while it runs.
Restart your editor afterwards. That's it.
Signed-in commands on an existing machine
The dashboard's Generate signed-in command creates a one-use setup link for your account. Setup keeps a valid key for the same account. If this machine belongs to a different account, setup requires an interactive confirmation before replacing its saved credentials.
A piped command such as curl … | sh can still ask for confirmation when
run in a terminal: the installer reconnects to that terminal. In CI or a
container without a terminal, a different-account conflict stops setup and
leaves the existing credentials unchanged.
To switch accounts, open an interactive terminal, generate a fresh
signed-in command for the intended account, run it, and confirm the switch.
The failed attempt has already redeemed its one-use link, so reusing that
link cannot repeat the signed-in flow. Remove any conflicting
CONTEXTSTREAM_API_KEY or CONTEXTSTREAM_TOKEN value from that shell or CI
job; an environment credential can override the saved account. On shared
machines or in CI, use an isolated OS user configured for the intended
account instead of replacing another person's credentials unattended.
What changes after setup
Your assistant can now orient to the active project, retrieve context relevant to the current request, search the appropriate evidence, and preserve durable work when you ask. The generated instructions also tell it to stop when scope is ambiguous and to treat matching lessons as working guardrails.
ContextStream does not widen the assistant's execution permissions. You still control the goal and consequential actions; the connection removes repeated project explanation, not human authority. See how the agent partnership works for the full loop.
Check it worked
Ask your assistant something that requires project context from the connection:
what project am I in?
what did we decide about anything so far?The first should name your project. The second will be empty on day one — that's the correct answer, and it proves the connection.
Your editor's exact details
The setup wizard currently manages Claude Code, Cursor, GitHub Copilot in VS Code, Windsurf, Cline, Kilo, Roo, Codex CLI, Aider, Antigravity, and OpenCode. For each one you select, the wizard creates every supported connection and instruction file automatically. On editors with lifecycle support, it also installs the automation that surfaces relevant context and guardrails while you work. Aider supports instruction rules only. Claude Desktop is supported through manual configuration, but is not one of the wizard-managed targets. Custom MCP connectors are not part of this wizard either: paste the hosted URL into any client that accepts a custom connector. See Connect ContextStream Custom MCP.
Pick yours to see its exact files and connection shape:
Claude Code
Hosted connectionAnthropic's terminal and IDE coding agent.
- Connection file
mcp.json~/.claude/mcp.json globally, or .mcp.json in a project- Instructions file
CLAUDE.mdProject root, or ~/.claude/CLAUDE.md globally
{
"mcpServers": {
"contextstream": {
"type": "http",
"url": "https://mcp.contextstream.io/mcp?default_context_mode=fast",
"headers": {
"X-ContextStream-API-Key": "YOUR_API_KEY"
}
}
}
}Replace YOUR_API_KEY with a key from your dashboard, keep the file out of version control, and restart the client. The setup command writes the fuller managed configuration for you.
Connecting more editors later
Run the setup again — it's safe to re-run and won't duplicate anything. Or use the maintenance commands in Keeping it current.
If it doesn't work
The assistant doesn't seem connected. Restart the editor. Most read MCP configuration only at startup.
It connected but knows nothing about the project. Indexing runs in the background and takes a few minutes on a large repository.
The script can't find my editor. It looks in standard install locations. Set it up by hand — see Set it up by hand.