Smithery MCP Server for OpenAI Agents SDK 11 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Smithery through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token — get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="Smithery Assistant",
instructions=(
"You help users interact with Smithery. "
"You have access to 11 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Smithery"
)
print(result.final_output)
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 Smithery MCP Server
What you can do
Connect AI agents to the Smithery Registry for comprehensive MCP server discovery and management:
The OpenAI Agents SDK auto-discovers all 11 tools from Smithery through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Smithery, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.
- Search MCP servers — find servers by name, description, or tags with semantic search
- Get server details — review metadata, verification status, and user counts
- Discover tools — list all tools (functions) exposed by any registered MCP server
- Discover resources — list all data resources available from MCP servers
- Discover prompts — list all prompt templates exposed by MCP servers
- Create connections — connect to MCP servers via Smithery Connect with automatic OAuth handling
- Manage connections — list, inspect, and remove MCP server connections
- Generate service tokens — create scoped, time-limited tokens for frontend/agent access
- View analytics — monitor server usage, adoption trends, and performance metrics
The Smithery MCP Server exposes 11 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Smithery to OpenAI Agents SDK via MCP
Follow these steps to integrate the Smithery MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 11 tools from Smithery
Why Use OpenAI Agents SDK with the Smithery MCP Server
OpenAI Agents SDK provides unique advantages when paired with Smithery through the Model Context Protocol.
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
Smithery + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Smithery MCP Server delivers measurable value.
Automated workflows: build agents that query Smithery, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents — one queries Smithery, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Smithery tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Smithery to resolve tickets, look up records, and update statuses without human intervention
Smithery MCP Tools for OpenAI Agents SDK (11)
These 11 tools become available when you connect Smithery to OpenAI Agents SDK via MCP:
create_connection
Smithery handles OAuth, tokens, and sessions automatically. Requires the server namespace and connection configuration (mcpUrl, optional headers, metadata). Returns the connection ID, status, and server info. Use this to integrate MCP servers into your applications without managing authentication complexity. Create a new connection to an MCP server via Smithery Connect
create_service_token
The token has limited permissions defined by the policy (namespaces, resources, operations, metadata, TTL). Returns the token string. Use this to provide secure, time-limited access to MCP servers without exposing your main API key. Generate a scoped service token for frontend/agent access to MCP servers
delete_connection
This action cannot be undone. Requires namespace and connection ID. Use this to clean up unused connections or revoke access. Remove an MCP server connection
get_connection
Requires namespace and connection ID. Use this to review connection details or troubleshoot connectivity issues. Get detailed information about a specific MCP connection
get_server_analytics
Requires the server qualified name. Use this to monitor server adoption, identify usage trends, or troubleshoot performance issues. Get usage analytics for a specific MCP server
get_server_details
Requires the qualified name (e.g., "smithery/hello-world" or "github/github") from search_servers results. Use this to review server capabilities before connecting. Get detailed information about a specific MCP server from the Smithery registry
get_server_prompts
Returns prompt names, descriptions, and argument definitions. Requires the server qualified name. Use this to discover reusable prompt workflows available from the server. List all prompt templates exposed by a specific MCP server
get_server_resources
Returns resource URIs, names, descriptions, and MIME types. Requires the server qualified name. Use this to understand what data the server provides read access to. List all resources exposed by a specific MCP server
get_server_tools
Returns tool names, descriptions, input schemas, and annotations. Requires the server qualified name. Use this to understand what actions the server can perform before connecting it to your agents. List all tools exposed by a specific MCP server
list_connections
Returns connection IDs, names, statuses, creation dates, and metadata. Use this to audit which connections are active, review connection configurations, or identify unused connections. List all connections for a specific MCP server namespace
search_servers
Returns matching servers with qualified names, descriptions, verification status, user counts, and deployment info. Use optional filters to narrow by namespace, verified status, or deployment state. Results include pagination metadata. Use this as the first step to discover available MCP servers before connecting or installing them. Search the Smithery registry for MCP servers by name, description, or tags
Example Prompts for Smithery in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Smithery immediately.
"Search for verified GitHub-related MCP servers"
"Show me all tools exposed by the Stripe MCP server"
"Create a connection to the Slack MCP server for my workspace"
Troubleshooting Smithery MCP Server with OpenAI Agents SDK
Common issues when connecting Smithery to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Smithery + OpenAI Agents SDK FAQ
Common questions about integrating Smithery MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
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?
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?
Connect Smithery with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Smithery to OpenAI Agents SDK
Get your token, paste the configuration, and start using 11 tools in under 2 minutes. No API key management needed.