zephex
⌘K
Get StartedPricingMCP ToolsDocs
←Back×Sign in
Get StartedPricingMCP ToolsDocs

Documentation

Start with the endpoint and API key flow, then branch into editor setup or tool reference.

GET STARTED

What is MCP?IntroductionQuickstartAPI ReferenceUniversal RequirementsZephex vs Local MCPBest PracticesToken EfficiencyCLAUDE.md TemplateAGENTS.md TemplateMCP EcosystemMarkdown Access

EDITORS

OpenCodeOAuthVS CodeClaude CodeCursorWindsurfJetBrainsKiro CLIOAuthZedOAuthGemini CLIOAuthClineOAuthGooseCodex CLIOAuthFactory AIOAuth

OPERATING SYSTEMS

macOSWindowsLinux

TOOLS

get_project_contextread_codefind_codecheck_packageaudit_packageexplain_architectureZephex_dev_infoscope_taskaudit_headersthinking

SUPPORT

PlansPro & Max GuideUsage & AnalyticsConnection IssuesRate LimitsBillingSecurityFAQChangelog

What is MCP? (Model Context Protocol)

MCP is the protocol layer that lets AI coding tools move beyond the context window and call real tools over a consistent interface.

MCP, or Model Context Protocol, is an open standard developed by Anthropic that defines how AI models communicate with external tools and data sources. It gives AI coding agents a structured way to call tools, read files, search codebases, audit security, and perform other tasks through a consistent JSON-RPC 2.0 interface.

Before MCP, AI coding assistants could only work with what was already in their context window. With MCP, they can reach outside that window and interact with real systems: your code, your packages, your HTTP endpoints, and your documentation.

HOW MCP WORKS

An MCP session usually works like this:

  1. An MCP client such as Cursor, Claude Code, or VS Code connects to an MCP server at startup.
  2. The client calls tools/list to discover what tools are available.
  3. During a coding session, the AI model calls tools/call with a tool name and arguments.
  4. The MCP server executes the tool and returns a structured result.
  5. The AI model sees the result and uses it to inform its next action.

The full exchange uses JSON-RPC 2.0, a simple request/response protocol carried over HTTP or stdio.

MCP TRANSPORT TYPES
TransportHow it worksWho manages the server
stdioServer runs as a local subprocess and communicates over stdin/stdout.You, locally on your machine.
HTTP (Streamable)Server runs remotely and communicates over HTTPS.The provider, in the cloud.

Most open-source MCP setups use stdio. You run a local server command and your editor talks to it as a subprocess. That works, but it also means you manage packages, processes, and config on every machine where you want MCP available.

WHY CLOUD-HOSTED MCP
  • No local processes to start or keep alive.
  • No per-machine npm or npx setup just to get tools running.
  • One endpoint that works from any editor, machine, or environment.
  • Auth, rate limiting, and billing handled by the provider.

HTTP transport changes the model entirely. Instead of running servers locally, your editor connects to a remote HTTPS endpoint. That is what Zephex provides.

HOW ZEPHEX IMPLEMENTS MCP

Zephex runs an MCP HTTP server at https://zephex.dev/mcp. Every request is authenticated with a Bearer token. The 10 available tools cover the most common AI coding agent needs: project orientation, code reading, pattern search, package intelligence, security auditing, and structured reasoning.

You configure your editor once with the endpoint URL and your API key. From that point on, every AI session in that editor has access to all 10 tools without any additional setup.

Start with the Quickstart to connect your first editor in under 5 minutes.