MCP in Practice: Building Tool Servers in Go
Model Context Protocol promises to standardize how AI talks to tools. I built an MCP server in Go to see if the promise holds up. Here's what I found.
Anthropic coverage in this archive spans 4 posts from Mar 2023 to Mar 2025 and treats anthropic as a production discipline: evaluation loops, tool boundaries, escalation paths, and cost control. The strongest adjacent threads are ai, claude, and llm. Recurring title motifs include claude, practice, tool, and servers.
Model Context Protocol promises to standardize how AI talks to tools. I built an MCP server in Go to see if the promise holds up. Here's what I found.
Anthropic's Claude 3.5 Sonnet isn't just another model release. It's a bet that the mid-tier can handle what you've been paying top-tier prices for.
Anthropic shipped three models instead of one. That is actually the most interesting part of the release.
Anthropic's Claude takes a different approach to AI safety. Here is how it compares to GPT in practice, from someone using both daily.