4,000+ servers built on vurb.ts
Vinkius

GetStream MCP Server for Mastra AIGive Mastra AI instant access to 23 tools to Add Activity To Feed, Add To Collection, Batch Delete Collections, and more

MCP Inspector GDPR Free for Subscribers

Mastra AI is a TypeScript-native agent framework built for modern web stacks. Connect GetStream through Vinkius and Mastra agents discover all tools automatically. type-safe, streaming-ready, and deployable anywhere Node.js runs.

Ask AI about this MCP Server for Mastra AI

The GetStream MCP Server for Mastra AI is a standout in the Productivity category — giving your AI agent 23 tools to work with, ready to go from day one.

Built for AI Agents by Vinkius

Vinkius delivers Streamable HTTP and SSE to any MCP client

ClaudeClaude
ChatGPTChatGPT
CursorCursor
GeminiGemini
WindsurfWindsurf
VS CodeVS Code
JetBrainsJetBrains
VercelVercel
+ other MCP clients
typescript
import { Agent } from "@mastra/core/agent";
import { createMCPClient } from "@mastra/mcp";
import { openai } from "@ai-sdk/openai";

async function main() {
  // Your Vinkius token. get it at cloud.vinkius.com
  const mcpClient = await createMCPClient({
    servers: {
      "getstream": {
        url: "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
      },
    },
  });

  const tools = await mcpClient.getTools();
  const agent = new Agent({
    name: "GetStream Agent",
    instructions:
      "You help users interact with GetStream " +
      "using 23 tools.",
    model: openai("gpt-4o"),
    tools,
  });

  const result = await agent.generate(
    "What can I do with GetStream?"
  );
  console.log(result.text);
}

main();
GetStream
Fully ManagedVinkius Servers
60%Token savings
High SecurityEnterprise-grade
IAMAccess control
EU AI ActCompliant
DLPData protection
V8 IsolateSandboxed
Ed25519Audit chain
<40msKill switch
Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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

About GetStream MCP Server

Connect GetStream to your AI agent to orchestrate complex social architectures and activity feeds using natural language.

Mastra's agent abstraction provides a clean separation between LLM logic and GetStream tool infrastructure. Connect 23 tools through Vinkius and use Mastra's built-in workflow engine to chain tool calls with conditional logic, retries, and parallel execution. deployable to any Node.js host in one command.

What you can do

  • Feed Management — Retrieve, add, or remove activities from specific feed slugs and user timelines using get_feed and add_activity_to_feed.
  • Activity Orchestration — Update activity metadata or perform partial updates to specific fields via partial_update_activity without rewriting entire objects.
  • Social Graph — Manage follower relationships, list who follows a feed, and perform follow operations using follow_feed and list_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.

The GetStream MCP Server exposes 23 tools through the Vinkius. Connect it to Mastra AI in under two minutes — credentials fully managed, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

All 23 GetStream tools available for Mastra AI

When Mastra AI connects to GetStream through Vinkius, your AI agent gets direct access to every tool listed below — spanning activity-feeds, chat-api, social-infrastructure, and more. Every call runs in a secure, isolated environment with full audit visibility. Beyond a simple connection, you get real-time monitoring of agent activity, enterprise governance, and optimized token usage.

add

Add activity to feed on GetStream

Add an activity to a feed

add

Add to collection on GetStream

Add objects to a collection

batch

Batch delete collections on GetStream

Batch delete collections

batch

Batch follow on GetStream

Batch follow multiple feeds

batch

Batch get collections on GetStream

Batch retrieve collections

batch

Batch post collections on GetStream

Batch create/update collections

delete

Delete collection object on GetStream

Delete an individual collection object

delete

Delete file on GetStream

Delete a file by URL

follow

Follow feed on GetStream

Follow a target feed

get

Get activities on GetStream

Retrieve specific activities by ID or foreign ID

get

Get collection object on GetStream

Retrieve an individual collection object

get

Get feed on GetStream

Supports pagination. Retrieve activities in a feed

get

Get open graph on GetStream

Scrape Open Graph data from a URL

list

List feed followers on GetStream

List feeds following this feed

list

List feed follows on GetStream

List feeds this feed follows

partial

Partial update activity on GetStream

Partially update activity data

process

Process image on GetStream

Process or resize an image

remove

Remove activity from feed on GetStream

Remove an activity from a feed

unfollow

Unfollow feed on GetStream

Unfollow a target feed

update

Update activities on GetStream

Update activity metadata

update

Update collection object on GetStream

Update an individual collection object

upload

Upload file on GetStream

Upload a file

upload

Upload image on GetStream

Upload an image

Connect GetStream to Mastra AI via MCP

Follow these steps to wire GetStream into Mastra AI. The entire setup takes under two minutes — your credentials stay safe behind Vinkius.

01

Install dependencies

Run npm install @mastra/core @mastra/mcp @ai-sdk/openai
02

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token
03

Run the agent

Save to agent.ts and run with npx tsx agent.ts
04

Explore tools

Mastra discovers 23 tools from GetStream via MCP

Why Use Mastra AI with the GetStream MCP Server

Mastra AI provides unique advantages when paired with GetStream through the Model Context Protocol.

01

Mastra's agent abstraction provides a clean separation between LLM logic and tool infrastructure. add GetStream without touching business code

02

Built-in workflow engine chains MCP tool calls with conditional logic, retries, and parallel execution for complex automation

03

TypeScript-native: full type inference for every GetStream tool response with IDE autocomplete and compile-time checks

04

One-command deployment to any Node.js host. Vercel, Railway, Fly.io, or your own infrastructure

GetStream + Mastra AI Use Cases

Practical scenarios where Mastra AI combined with the GetStream MCP Server delivers measurable value.

01

Automated workflows: build multi-step agents that query GetStream, process results, and trigger downstream actions in a typed pipeline

02

SaaS integrations: embed GetStream as a first-class tool in your product's AI features with Mastra's clean agent API

03

Background jobs: schedule Mastra agents to query GetStream on a cron and store results in your database automatically

04

Multi-agent systems: create specialist agents that collaborate using GetStream tools alongside other MCP servers

Example Prompts for GetStream in Mastra AI

Ready-to-use prompts you can give your Mastra AI agent to start working with GetStream immediately.

01

"Show me the latest activities in the 'user' feed for user ID 'user_123'."

02

"Make the feed 'timeline:alice' follow 'user:bob'."

03

"Update activity ID 'act_999' to set the 'is_featured' field to true."

Troubleshooting GetStream MCP Server with Mastra AI

Common issues when connecting GetStream to Mastra AI through Vinkius, and how to resolve them.

01

createMCPClient not exported

Install: npm install @mastra/mcp

GetStream + Mastra AI FAQ

Common questions about integrating GetStream MCP Server with Mastra AI.

01

How does Mastra AI connect to MCP servers?

Create an MCPClient with the server URL and pass it to your agent. Mastra discovers all tools and makes them available with full TypeScript types.
02

Can Mastra agents use tools from multiple servers?

Yes. Pass multiple MCP clients to the agent constructor. Mastra merges all tool schemas and the agent can call any tool from any server.
03

Does Mastra support workflow orchestration?

Yes. Mastra has a built-in workflow engine that lets you chain MCP tool calls with branching logic, error handling, and parallel execution.

Explore More MCP Servers

View all →