How deeply does AI Agents in Action, Second Edition cover server-sent events?

Explains deployment choices and configuration examples, but stops short of detailing the SSE protocol internals.

Server-sent events in AI Agents in Action, Second Edition

Server-Sent Events is an HTTP-based protocol for streaming event updates from a server to a client over a persistent connection.

Server-Sent Events (SSE) is an HTTP-based transport for streaming updates from a server to a client over a persistent connection. In MCP deployments, it connects an agent to a server outside the agent process, unlike STDIO, which uses local process pipes. section 3.1.4 section 3.2.3

Use SSE when the server needs to remain independently accessible:

Connect agents to MCP servers running on another machine, container, or cloud resource. section 3.3
Share one tool server across multiple agents instead of restricting access to the process that launched it. section 3.1.4 section 3.3.2
Choose local STDIO instead when low latency, simple process management, and single-machine access matter more than remote access. section 3.1.4 section 3.3

Run and connect to an SSE MCP server

Start the server externally with `mcp run -t sse 01_claude_mcp_server.py`. Then configure an MCP SSE client with the URL `http://localhost:8000/sse`, rather than a server command and arguments. The agent can keep the same tool-using logic while the transport changes from STDIO to SSE. section 3.3.2 section 3.5

Table 3.1 Differences between STDIO and SSE transports for MCP servers

Name	How it works	When you should use it
STDIO	The client launches the MCP server as a subprocess on the same host and exchanges JSON-RPC 2.0 messages over the process’s stdin/stdout pipes. No networking stack is involved, so the link is low-latency but strictly one-to-one: only the parent process that spawned the server can talk to it.	Local development or quick CLI experiments where you want to keep everything in a single shell session. Command-line tools or scripts that spin up a helper MCP server just for the task at hand (e.g., mcp dev my_server.py). Containers that you run interactively (docker run -it …) and communicate with via stdio to avoid opening ports. Simple process-to-process integrations that don’t need remote access, reverse proxies, or multiclient support.
SSE	The MCP server runs as an HTTP service. Clients post JSON-RPC requests to /messages, while the server streams responses and notifications back over a long-lived text/event-stream connection (server-sent events), such as /sse. This makes the channel half-duplex (client > server via HTTP POST, server > client via SSE) but fully network addressable and capable of serving many clients concurrently.	Remote or cloud deployments where tools must be reachable over the network or behind a reverse proxy/load balancer. Browser-based or front-end apps that need real-time streaming (token-by-token LLM output) without WebSocket complexity; SSE works through most firewalls and proxies.

Compare SSE with STDIO by protocol, network involvement, connection scope, and recommended deployment scenarios. section 3.2.3

How AI Agents in Action, Second Edition covers it

Also explained in

Related concepts

This explainer was generated by Manning's knowledge graph from the text of AI Agents in Action, Second Edition. The section links point to the parts of the book it draws on.