GetStream MCP Server for Pydantic AIGive Pydantic AI instant access to 23 tools to Add Activity To Feed, Add To Collection, Batch Delete Collections, and more
GDPR Free for SubscribersPydantic AI brings type-safe agent development to Python with first-class MCP support. Connect GetStream through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.
Ask AI about this MCP Server for Pydantic AI
The GetStream MCP Server for Pydantic AI is a standout in the Productivity category — giving your AI agent 23 tools to work with, ready to go from day one.
Vinkius delivers Streamable HTTP and SSE to any MCP client
Geminiimport asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
agent = Agent(
model="openai:gpt-4o",
mcp_servers=[server],
system_prompt=(
"You are an assistant with access to GetStream "
"(23 tools)."
),
)
result = await agent.run(
"What tools are available in GetStream?"
)
print(result.data)
asyncio.run(main())
* 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.
Pydantic AI validates every GetStream tool response against typed schemas, catching data inconsistencies at build time. Connect 23 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
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.
The GetStream MCP Server exposes 23 tools through the Vinkius. Connect it to Pydantic 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 Pydantic AI
When Pydantic 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 activity to feed on GetStream
Add an activity to a feed
Add to collection on GetStream
Add objects to a collection
Batch delete collections on GetStream
Batch delete collections
Batch follow on GetStream
Batch follow multiple feeds
Batch get collections on GetStream
Batch retrieve collections
Batch post collections on GetStream
Batch create/update collections
Delete collection object on GetStream
Delete an individual collection object
Delete file on GetStream
Delete a file by URL
Follow feed on GetStream
Follow a target feed
Get activities on GetStream
Retrieve specific activities by ID or foreign ID
Get collection object on GetStream
Retrieve an individual collection object
Get feed on GetStream
Supports pagination. Retrieve activities in a feed
Get open graph on GetStream
Scrape Open Graph data from a URL
List feed followers on GetStream
List feeds following this feed
List feed follows on GetStream
List feeds this feed follows
Partial update activity on GetStream
Partially update activity data
Process image on GetStream
Process or resize an image
Remove activity from feed on GetStream
Remove an activity from a feed
Unfollow feed on GetStream
Unfollow a target feed
Update activities on GetStream
Update activity metadata
Update collection object on GetStream
Update an individual collection object
Upload file on GetStream
Upload a file
Upload image on GetStream
Upload an image
Connect GetStream to Pydantic AI via MCP
Follow these steps to wire GetStream into Pydantic AI. The entire setup takes under two minutes — your credentials stay safe behind Vinkius.
Install Pydantic AI
pip install pydantic-aiReplace the token
[YOUR_TOKEN_HERE] with your Vinkius tokenRun the agent
agent.py and run: python agent.pyExplore tools
Why Use Pydantic AI with the GetStream MCP Server
Pydantic AI provides unique advantages when paired with GetStream through the Model Context Protocol.
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your GetStream integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your GetStream connection logic from agent behavior for testable, maintainable code
GetStream + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the GetStream MCP Server delivers measurable value.
Type-safe data pipelines: query GetStream with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple GetStream tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query GetStream and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock GetStream responses and write comprehensive agent tests
Example Prompts for GetStream in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with GetStream immediately.
"Show me the latest activities in the 'user' feed for user ID 'user_123'."
"Make the feed 'timeline:alice' follow 'user:bob'."
"Update activity ID 'act_999' to set the 'is_featured' field to true."
Troubleshooting GetStream MCP Server with Pydantic AI
Common issues when connecting GetStream to Pydantic AI through Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiGetStream + Pydantic AI FAQ
Common questions about integrating GetStream MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.Does Pydantic AI validate MCP tool responses?
Can I switch LLM providers without changing MCP code?
Explore More MCP Servers
View all →
Mattermost (Secure Team Collaboration)
10 toolsManage team collaboration via Mattermost — send messages, search channels, and audit team activities.
Fireblocks
40 toolsSecurely manage digital assets, vault accounts, and blockchain transactions via the Fireblocks Digital Asset Platform directly from your AI agent.
Clover
10 toolsManage orders, payments, inventory, customers, employees, and discounts for your Clover POS through natural conversation.
Hugging Face
15 toolsAccess thousands of pre-trained AI models for NLP, vision, and audio tasks with the largest open-source machine learning hub.