> 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/mcp-servers.md). # MCP Servers The MCP Servers page provides an organization-wide view of all Model Context Protocol (MCP) servers configured across developer machines. MCP servers extend AI agents by enabling them to interact with external systems, APIs, and local tools. This page helps you understand where those integrations exist and how widely they are deployed.
Filter chips let you scope the list by **Transport** (`Local` or `Remote`) and by **Config source**, with each chip showing how many servers match. The MCP server table shows the following columns: * **Server**: the MCP server name (for example, `npx~server-brave-search`, `npx~server-filesystem`) * **Transport**: how the server is invoked: `Local` for a process started on the device, or `Remote` for a server reached over the network * **Config Sources**: the AI tools that have this server registered in their configuration (for example, `cursor`, `antigravity`, `windsurf`). Multiple sources may be shown per row when the same server is configured by more than one tool. `Claude Code plugin` and `Codex plugin` mean the server is supplied by an installed agent plugin, and `Discovered` means the configuration file was found on disk rather than read from a known tool's configuration. * **Plugin**: for a server supplied by an agent plugin, the plugin it comes from. Select it to open the plugin on the [Agent Plugins](/developer-machines/ide-and-ai-agents/agent-plugins.md) page. * **Devices**: the number of devices where the server is configured ### Expanding a Server Each MCP server row can be expanded to view device-level details. When expanded, you can see: * **Device ID**: the unique identifier of the developer machine * Configuration or execution details where applicable This allows you to: * Identify which machines have a specific MCP server configured * Detect duplicate or redundant configurations * Investigate potentially risky integrations * Validate compliance with approved MCP server policies

Agent plugin marketplaces are catalogs, and each catalog entry can ship a template .mcp.json for a plugin that is not installed. Those templates are not reported as MCP servers. A plugin's own MCP servers are reported only when the plugin is installed, and are attributed to that plugin. Requires agent v1.17.0 or later.

--- # 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 by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.stepsecurity.io/developer-machines/ide-and-ai-agents/mcp-servers.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.