How to Use the GetStream MCP in Claude Code
Automate GetStream feed operations from the command line with Claude Code. Built for CI/CD and cron jobs.
Works with every AI agent you already use
…and any MCP-compatible client
Connect GetStream MCP to Claude Code
Create your Vinkius account to connect GetStream to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.
Script Your Feeds in Shell
This MCP Server connects GetStream's API to your terminal. It's built for headless automation. Pipe the output of `list_feed_followers` to another command or trigger `add_activity_to_feed` from a bash script. Forget writing custom API clients for your build scripts. Just use Claude Code. Announce a successful deployment to a team feed, or use `get_activities` in a cron job to check for stale data and send an alert if anything looks wrong. It's just another tool in your pipeline.
Headless Data Migration and Management
Run large-scale GetStream operations from any terminal. This is perfect for data migrations or bulk updates. Use `batch_follow` to onboard a new department or `batch_post_collections` to backfill data for a new feature. The output is standard JSON, so you can easily pipe it to `jq` for filtering or save it to a file. Need to delete test data after a CI run? A single line calling `batch_delete_collections` does the job. No UI, no fuss.
Monitor and Maintain from the CLI
Build powerful monitoring scripts for your GetStream integration. Use Claude Code to call `get_feed` on a critical feed and check the timestamp of the last activity. If it's too old, pipe an alert to your monitoring system. This turns GetStream's API into a set of command-line utilities. You can check the health of your social graph with `list_feed_follows` or verify file uploads are working by calling `upload_file` and `delete_file` in a test script. It's a solid way to build operational resilience.
Set up GetStream MCP in Claude Code
Prerequisites
- Claude Code CLI installed (
npm install -g @anthropic-ai/claude-code) - Active Vinkius subscription with a valid endpoint token
- 1
Run the add command
Open your terminal and run the command shown on the right. Replace
[YOUR_TOKEN_HERE]with your endpoint token from cloud.vinkius.com. Use--scope userto make it available across all projects. - 2
Verify the connection
Start a Claude Code session and type
/mcpto list connected servers. You should seegetstream-mcpwith a green status indicator. - 3
Start using tools
Ask Claude Code something like "Check my latest GetStream transactions." It will automatically discover and invoke the available GetStream tools.
claude mcp add --transport http getstream-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Why Choose Vinkius
Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.
Real-time monitoring
Live
visibility into every interaction
Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.
Built-in savings
60%
lower AI costs
Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.
Single dashboard
One
place for every integration
Every tool your AI connects to, managed from a single screen. One account, complete control.
Common questions about GetStream MCP in Claude Code
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the GetStream MCP today
We host it, we monitor it, we maintain it. You just paste one token.