> For the complete documentation index, see [llms.txt](https://docs.stepsecurity.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stepsecurity.io/developer-machines/ide-and-ai-agents.md). # IDE & AI Agents A modern development setup is no longer one editor. It is a coding tool, the extensions installed into it, the MCP servers it is wired to, and the skills it loads at runtime. Each of those is installed separately, updates on its own schedule, and runs with the developer's own privileges. This section inventories all four across your fleet, so you can see what your developers are actually running rather than what was approved. ### What each page answers | Page | The question it answers | | ------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Coding Tools](/developer-machines/ide-and-ai-agents/coding-tools.md) | Which AI coding tools, CLI agents, IDEs, and local model runtimes are installed, on how many machines, and at which versions. | | [IDE Extensions](/developer-machines/ide-and-ai-agents/ide-extensions.md) | Which extensions and plugins are installed in those IDEs, what each one scores on supply chain signals, and whether any are known to be compromised or typosquatted. | | [MCP Servers](/developer-machines/ide-and-ai-agents/mcp-servers.md) | Which MCP servers the agents are configured to call, how they are invoked, and which tool's configuration registered them. | | [Agent Skills](/developer-machines/ide-and-ai-agents/agent-skills.md) | Which skills the agents can load, where each came from, whether it ships executable content, and whether every machine is running the same version of it. | ### How the layers fit together The four inventories describe one stack, and the interesting questions cross between them. A developer installs Cursor, which appears under **Coding Tools**. They add extensions to it, which appear under **IDE Extensions**. They wire it to an MCP server so the agent can reach a ticketing system or the local filesystem, and that configuration appears under **MCP Servers**, attributed to Cursor as its config source. They drop a skill into a skills directory so the agent handles a recurring task the same way each time, and that appears under **Agent Skills**. Each layer can execute code as the developer. An extension runs inside the IDE. An MCP server is a process the agent starts. A skill can ship scripts, register hooks, and embed shell commands. So "which AI tools do we use" is rarely the question that matters. The useful questions run down the stack: * An agent is compromised upstream. Which machines run it, and which of them also hold cloud credentials? That is **Coding Tools** into Credentials. * An MCP server turns out to be malicious. Which tool's config registered it, and on how many machines? That is **MCP Servers**, where the config source tells you which agent to look at. * A skill is shared through a repository. Are all machines running the same content, or has one drifted? That is **Agent Skills**, where content hashes make divergence visible. ### Where to start * **Take stock of what is in use.** Start with Coding Tools and filter by category. Most organizations find agents they did not know were deployed. * **Look for known-bad extensions.** IDE Extensions flags compromised and typosquatted items directly, which is the fastest route to something actionable. * **Review what the agents can reach.** MCP Servers shows the integrations, and remote transports are worth a closer look than local ones. * **Check an extension before it is installed.** Extension Advisor scores any extension by id, whether or not anyone in your organization has it. * **Enforce a decision.** Allow-lists and block-lists for VS Code extensions are available through Device Policy. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.stepsecurity.io/developer-machines/ide-and-ai-agents.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.