mcp-server-sse

Configure and connect HTTP SSE MCP servers for OpenAI Agents SDK.

Updated Dec 7, 2025
One-click install
npx skills add https://github.com/syeda-hoorain-ali/todo-spec-driven-hackathon --skill mcp-server-sse
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-server-sse
Source: https://github.com/syeda-hoorain-ali/todo-spec-driven-hackathon/tree/main/.claude/skills/mcp-server-sse
Command: npx skills add https://github.com/syeda-hoorain-ali/todo-spec-driven-hackathon --skill mcp-server-sse

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

HTTP SSE MCP server configuration and connection setup for OpenAI Agents SDK, simplifying integration and ensuring reliable real-time communication.

Core Features & Use Cases

  • MCPServerSse connection configuration and parameter validation for MCP-based agents.
  • Real-time SSE transport to stream MCP events from servers.
  • Optional headers, timeouts, and customizable httpx client behavior for flexible deployments.
  • Use Case: Attach MCPServerSse to an AI agent to enable live MCP tool discovery and execution over SSE.

Quick Start

Instantiate MCPServerSse with a URL and optional headers, then attach it to an Agent and run a test query.

Frequently Asked Questions about mcp-server-sse

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure an SSE MCP server for OpenAI Agents?

An SSE MCP server uses HTTP Server-Sent Events to stream real-time data from MCP servers to OpenAI Agents. It enables live tool discovery and execution, allowing AI agents to access and interact with external tools dynamically over the network.

What parameters are available when setting up MCPServerSse?

MCPServerSse setup parameters include url, headers, timeout, sse_read_timeout, httpx_client_factory, cache_tools_list, name, tool_filter, use_structured_content, max_retry_attempts, retry_backoff_seconds_base, and message_handler for production-ready deployments.

Can I customize httpx client behavior and timeouts for SSE MCP connections?

Yes, you can customize httpx client behavior and timeouts for SSE MCP connections using the httpx_client_factory, timeout, and sse_read_timeout parameters. This allows flexible deployments across local and cloud environments with reliable streaming.

Does the SSE MCP server configuration support retry logic and error handling?

The SSE MCP server configuration supports retry logic through max_retry_attempts and retry_backoff_seconds_base parameters. It also implements input validation and safety checks to ensure reliable real-time communication between agents and servers.

When should I use SSE transport instead of standard HTTP for MCP servers?

Use SSE transport for MCP servers when your AI agent workflows require real-time event streaming and live tool discovery. SSE provides continuous streaming from servers, making it ideal for scenarios needing immediate updates and seamless tool access.