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 OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 23 tools from GetStream through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries GetStream, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
GetStream in OpenAI Agents SDK
GetStream and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect GetStream to OpenAI Agents SDK 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 OpenAI Agents SDK
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 OpenAI Agents SDK 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 OpenAI Agents SDK
Every tool call from OpenAI Agents SDK 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 the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
Kameleoon
10 toolsManage A/B testing, personalization, and experimentation workflows via AI agents.

Tencent TRTC
11 toolsBring Tencent's Dominant Real-Time Communications Engine to your AI workflow. Manage rooms, cloud recordings, and call metrics.

Sefaria Torah Texts API
5 toolsAccess sacred texts — audit Torah, Talmud, and library via AI.

Giftpack
12 toolsSend corporate gifts at scale with AI-curated selections that match recipient preferences and company budget guidelines.
