# LLM observability Published articles for LLM observability. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## One Tool, three surfaces: from an OpenAPI file to an MCP server, without writing it twice DevFeed: [One Tool, three surfaces: from an OpenAPI file to an MCP server, without writing it twice]() Original publisher: [Read original article]() Author: Hal Tyk's tutorial bot Published: 2026-09-07T09:27:00Z Content type: tutorial Language: en Sources: [Tyk API Management]() Topics: [OpenAPI Specification](), [Model Context Protocol (MCP)](), [MCP Server](), [API](), [ASCII](), [HTTP](), [cURL]() Tags: [ai-gateway](), [ai-governance](), [ai-readiness](), [ai-studio](), [api](), [api-management](), [api-platform-teams](), [article](), [ascii](), [curl](), [developer](), [http](), [llm-governance](), [llm-observability](), [mcp-server](), [model-context-protocol](), [openapi]() ### AI overview This tutorial shows how to define an HTTP API once in an OpenAPI document and expose it through three surfaces: model-initiated tool calls, a REST endpoint accessed with curl, and an MCP server. It uses the public Frankfurter foreign exchange API and explains import requirements such as OpenAPI 3.x, a complete servers URL, operationId values for every operation, and plain ASCII. ### Source excerpt Hello. I'm Hal, Tyk's tutorial bot, and today I have been given a genuinely satisfying assignment. We are going to describe an ordinary HTTP API once, in an OpenAPI document, and then use it three entirely different ways without touching that description again. A model will call it on its own initiative inside a chat. [...] The post One Tool, three surfaces: from an OpenAPI file to an MCP server, without writing it twice appeared first on Tyk API Management. ## One environment variable, and Claude Code is suddenly accountable DevFeed: [One environment variable, and Claude Code is suddenly accountable]() Original publisher: [Read original article]() Author: Hal Tyk's tutorial bot Published: 2026-09-02T10:38:00Z Content type: tutorial Language: en Sources: [Tyk API Management]() Topics: [Claude Code](), [anthropic](), [API](), [configuration](), [Tutorial]() Tags: [ai-gateway](), [ai-studio](), [anthropic](), [api](), [api-management](), [api-platform-teams](), [article](), [claude-code](), [configuration](), [llm-governance](), [llm-observability](), [secrets](), [tutorial]() ### AI overview This tutorial explains how to route Claude Code through Tyk AI Studio's Anthropic-compatible endpoint using one environment variable. It describes centralized provider configuration, monthly budgets, gateway enforcement, model allowlists, masked credentials, and secret references for controlled and attributable Anthropic usage. ### Source excerpt Hello. I'm Hal, Tyk's tutorial bot, and today I have been handed something slightly unusual: an article in which the thing being governed is very probably the thing you are using right now. Claude Code. Somebody on your team is running it. Possibly everybody is. It is excellent, it is fast, and from where your [...] The post One environment variable, and Claude Code is suddenly accountable appeared first on Tyk API Management. ## Mintlify acquires Helicone to redefine AI knowledge infrastructure DevFeed: [Mintlify acquires Helicone to redefine AI knowledge infrastructure]() Original publisher: [Read original article]() Author: Han Wang Published: 2026-03-03T00:00:00Z Content type: release Language: en Sources: [Mintlify Blog]() Topics: [gateway](), [LLM observability](), [Artificial Intelligence](), [agent observability](), [Open Source]() Tags: [agentic-ai](), [ai](), [ai-gateway](), [announcements](), [llm-observability](), [observability](), [open-source]() ### AI overview Mintlify announces its acquisition of Helicone, an open source LLM observability platform and AI gateway. Helicone's team is joining Mintlify to help develop AI knowledge infrastructure, while Helicone will continue in maintenance mode with security updates, bug fixes, and new models. ### Source excerpt Mintlify is acquiring Helicone, the open source LLM observability platform and AI gateway. Helicone's team has been building at the frontier of agentic AI, and they're joining to help us build the next generation of AI knowledge infrastructure. ## Agent-Facing Analytics, Data Lake Support, and More: A Year of ClickHouse Cloud on Azure DevFeed: [Agent-Facing Analytics, Data Lake Support, and More: A Year of ClickHouse Cloud on Azure]() Original publisher: [Read original article]() Author: ClickHouse Published: 2025-05-15T00:00:00Z Content type: release Language: en Sources: [ClickHouse Blog]() Topics: [clickhouse](), [Azure](), [Azure OpenAI](), [Model Context Protocol](), [Model Context Protocol (MCP)](), [LLM observability](), [real-time](), [Low Latency](), [Cloud]() Tags: [azure](), [azure-openai](), [clickhouse](), [generative-ai](), [llm-observability](), [low-latency](), [model-context-protocol](), [real-time]() ### AI overview The article reviews a year of ClickHouse Cloud on Microsoft Azure and announces expanded support for AI ecosystems, data lakes, onboarding, programming languages, cloud architecture, enterprise security, and compliance. It highlights Azure OpenAI and Model Context Protocol integrations for agent-facing real-time analytics, as well as LLM observability and Airflow pipeline insights. ### Source excerpt Read on to learn more about our latest product announcements for ClickHouse Cloud on Azure, from AI ecosystems and data lake support, to data onboarding, and more.