Compatible with every major AI agent and IDE
What is the GetStream MCP Server?
Connect GetStream to your AI agent to orchestrate complex social architectures and activity feeds using natural language.
What you can do
- Feed Management — Retrieve, add, or remove activities from specific feed slugs and user timelines using
get_feedandadd_activity_to_feed. - Activity Orchestration — Update activity metadata or perform partial updates to specific fields via
partial_update_activitywithout rewriting entire objects. - Social Graph — Manage follower relationships, list who follows a feed, and perform follow operations using
follow_feedandlist_feed_followers. - Collections & Files — Handle collection objects and manage file/image uploads for rich media experiences.
- Open Graph — Retrieve Open Graph data for URLs to enrich activity content automatically.
How it works
- Subscribe to this server
- Enter your Stream API Key and JWT Token
- Start managing your social infrastructure from any MCP-compatible client
Who is this for?
- Product Managers — monitor feed health and activity patterns without technical dashboards.
- Developers — test feed logic and activity updates directly from the IDE to speed up social feature integration.
- Community Managers — manage social graphs and moderate feed content through natural conversation.
Built-in capabilities (23)
Add an activity to a feed
Add objects to a collection
Batch delete collections
Batch follow multiple feeds
Batch retrieve collections
Batch create/update collections
Delete an individual collection object
Delete a file by URL
Follow a target feed
Retrieve specific activities by ID or foreign ID
Retrieve an individual collection object
Supports pagination. Retrieve activities in a feed
Scrape Open Graph data from a URL
List feeds following this feed
List feeds this feed follows
Partially update activity data
Process or resize an image
Remove an activity from a feed
Unfollow a target feed
Update activity metadata
Update an individual collection object
Upload a file
Upload an image
Why Claude Desktop?
Claude Desktop is the definitive way to connect GetStream to your AI workflow. Add Vinkius Edge URL to your config, restart the app, and Claude immediately exposes all 23 tools in the chat interface. ask a question, Claude calls the right tool, and you see the answer. Zero code, zero context switching.
- —
Claude Desktop is the reference MCP client. it was designed alongside the protocol itself, ensuring the most complete and stable MCP implementation available
- —
Zero-code configuration: add a server URL to a JSON file and Claude instantly discovers and exposes all available tools in the chat interface
- —
Claude's extended thinking capability lets it reason through multi-step tool usage, chaining multiple API calls to answer complex questions
- —
Enterprise-grade security with local config storage. your tokens never leave your machine, and connections go directly to Vinkius Edge network
GetStream in Claude Desktop
GetStream and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect GetStream to Claude Desktop through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for GetStream in Claude Desktop
The GetStream MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 23 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Claude Desktop only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
GetStream for Claude Desktop
Every tool call from Claude Desktop to the GetStream MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I retrieve specific activities using their unique identifiers?
Yes. Use the get_activities tool by providing a comma-separated list of activity IDs or foreign IDs to fetch their full metadata.
How do I check which feeds a specific user is currently following?
You can use the list_feed_follows tool. Provide the feed slug and user ID to get a comprehensive list of all target feeds being followed.
Is it possible to update only a single field in an activity without sending the whole object?
Absolutely. The partial_update_activity tool allows you to set or unset specific fields on an activity using a JSON payload, preserving the rest of the data.
How does Claude Desktop discover MCP tools?
When Claude Desktop starts, it reads the claude_desktop_config.json file and connects to each configured MCP server. It calls the tools/list endpoint to fetch the schema for every available tool, then surfaces them as clickable options in the chat interface via the 🔌 icon.
What happens if the MCP server is temporarily unavailable?
Claude Desktop handles disconnections gracefully. if the server is unreachable at startup, the tools simply won't appear. Once the server becomes available again, restarting Claude Desktop will re-establish the connection. There is no timeout penalty or error loop.
Can I connect multiple MCP servers simultaneously?
Yes. You can add as many servers as you need in the mcpServers section of the config file. Each server appears as a separate tool provider, and Claude can use tools from multiple servers in a single conversation turn.
Is there a limit on the number of tools per server?
Claude Desktop can handle hundreds of tools per server. However, for optimal LLM performance, Vinkius servers are designed to expose focused, well-documented tool sets rather than overwhelming the model with too many options.
Does Claude Desktop support Streamable HTTP transport?
Yes. Claude Desktop supports both SSE (Server-Sent Events) and the newer Streamable HTTP transport that Vinkius uses. Simply provide the server URL. Claude auto-negotiates the transport protocol.
Server not appearing after restart
Ensure the JSON is valid (no trailing commas). Check the file path: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\\Claude\\ (Windows).
Authentication error
Verify your Vinkius token is correct. Go to cloud.vinkius.com to regenerate it if needed.
Tools not showing in chat
Click the 🔌 icon at the bottom of the chat input. If it shows 0 tools, the server may still be connecting. wait a few seconds.
Explore More MCP Servers
View all →
Hotjar (Behavior Analytics)
10 toolsAnalyze user behavior via Hotjar — list sites, retrieve survey responses, and manage feedback widgets.

Meme Generator
2 toolsUniversal meme engine — generate custom memes using popular templates via AI.

GitGuardian
49 toolsAutomate secret detection and incident response via GitGuardian — manage secret incidents, deploy honeytokens, and audit workspace security directly from your AI agent.

Google Fonts API
4 toolsManage web fonts — audit families, variants, and categories via AI.
