https://step.dev/knowledgebase/30/ai/mcp_server/ Recent content in Step MCP Server on Step Documentation Hugo -- gohugo.io en Mon, 29 Jun 2026 00:00:00 +0000 https://step.dev/knowledgebase/30/ai/mcp_server/getting-started/ Mon, 08 Jun 2026 00:00:00 +0000 https://step.dev/knowledgebase/30/ai/mcp_server/getting-started/ Overview The Step MCP Server lets AI assistants and coding agents (such as Claude Code, Claude Desktop, and Cursor) drive the Step automation platform through the Model Context Protocol (MCP). It brings AI-powered software testing into your existing automation workflows: agents can author, run, and analyse test executions on Step without leaving their environment. Instead of clicking through the UI, you can triage a failed run (even a load test with thousands of failures) by asking in plain language and getting a cited root-cause summary back. https://step.dev/knowledgebase/30/ai/mcp_server/multi-profile-config/ Mon, 29 Jun 2026 00:00:00 +0000 https://step.dev/knowledgebase/30/ai/mcp_server/multi-profile-config/ The Step MCP Server supports a YAML-based configuration file that lets you define multiple profiles — each targeting a different Step instance or project. This is the recommended approach when you work with more than one Step instance, or manage many projects on the same instance. For the simple single-instance setup using environment variables, see Getting Started. Key concepts: profiles and projects A profile is a connection identity: a Step instance URL, an API token, and an optional default project. https://step.dev/knowledgebase/30/ai/mcp_server/tools/ Mon, 29 Jun 2026 00:00:00 +0000 https://step.dev/knowledgebase/30/ai/mcp_server/tools/ Reference for all tools exposed by the Step MCP Server. For setup and installation, see Getting Started. All tools accept two optional shared parameters: profile (which Step instance and credentials to use) and project (which project to act on). The discovery tools below are the exception: they don’t require a project. When omitted, parameters fall back to the configured defaults (see Profile and project resolution). Every tool’s response includes a resolvedContext block reporting the profile, baseUrl, and project actually used.