How to Use the GetStream MCP in Claude

Q: How do I configure GetStream within the Claude Desktop app?

Open your local claudedesktopconfig.json file. Add the server under the mcpServers key with your token, then restart the application to expose all 23 social feed tools via this MCP Server.

Q: Can Claude Desktop handle bulk feed operations through GetStream?

Yes. The agent uses batchfollow and batchpostcollections to execute high-volume database modifications in a single turn, which avoids hitting rate limits during testing.

Q: How do I test pagination inside the chat?

Ask the agent to run getfeed with specific limit parameters. The tool returns structured JSON payloads containing feed cursors, allowing you to debug deep-page performance directly in your chat window.

Spin up activity feeds and manage social graphs directly from Claude Desktop.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GetStream MCP to Claude Desktop

Create your Vinkius account to connect GetStream to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup GetStream with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run feed operations from Claude Desktop

The `add_activity_to_feed` tool lets your agent write new activities directly to GetStream while you chat in Claude Desktop. Instead of writing boilerplate curl requests, you ask the Claude Desktop client to inspect your active feeds using `get_feed` or strip out broken entries with `remove_activity_from_feed`. This setup lets you test your GetStream feed architecture in real-time without leaving your Claude Desktop conversation. You can update activity metadata on the fly with `update_activities` to see how the Claude Desktop interface renders the updated JSON payloads.

Control social graphs with this MCP Server

The `follow_feed` tool connects user feeds and constructs your GetStream social graph right inside the Claude Desktop interface. Your agent handles complex connection logic by calling `batch_follow` to link multiple feeds at once inside the Claude Desktop chat window. You can query follower counts using `list_feed_followers` or inspect outgoing connections with `list_feed_follows` directly within the Claude Desktop app. Having this GetStream MCP Server active means your agent diagnoses broken follow loops and tests timeline fan-out behaviors on the spot without leaving Claude Desktop.

Process media and sync collections

The `upload_image` tool handles asset ingestion and processes images using `process_image` to prepare them for your GetStream feed inside Claude Desktop. Claude Desktop reads local images directly from your hard drive, then hands them to the GetStream server to populate feeds with rich media. You can scrape link previews using `get_open_graph` and group feed objects with `add_to_collection` inside the Claude Desktop window. The entire assets workflow runs through this local GetStream MCP setup, letting you test media pipelines directly in Claude Desktop before writing any backend code.

Setup guide

Set up GetStream MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The GetStream MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the GetStream MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under getstream-mcp.

json

{
  "mcpServers": {
    "getstream-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by GetStream. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect GetStream now

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 Desktop

Open your local claude_desktop_config.json file. Add the server under the mcpServers key with your token, then restart the application to expose all 23 social feed tools via this MCP Server.

Yes. The agent uses batch_follow and batch_post_collections to execute high-volume database modifications in a single turn, which avoids hitting rate limits during testing.

The desktop app reads files from your machine and passes them to the upload_file or upload_image tool. This uploads the assets directly to the CDN, returning a URL to attach to your activities.

Ask the agent to run get_feed with specific limit parameters. The tool returns structured JSON payloads containing feed cursors, allowing you to debug deep-page performance directly in your chat window.

This server processes your activity feeds, social graph connections, and uploaded media files. All data is isolated within Vinkius's secure, ephemeral V8 sandboxes, meaning your API tokens and feed payloads never persist on the hosting infrastructure.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript