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

scope_task

Given a task description and project path, returns the minimum files to read, utilities to reuse, and the callers that are most likely to break.

DESCRIPTION

This is the highest-leverage planning tool in the set. Call it before you start reading files. It tells an agent where to look first and, just as important, which files it can ignore for now.

WHEN TO USE

GOOD FIT

  • At the start of every non-trivial coding task.
  • When you do not know which files a change will touch.
  • When you want to reuse existing utilities instead of reimplementing them.
  • When you want to reduce wasted context before any code reading begins.

AVOID IT WHEN

  • You already know the exact file set and just need the implementation details.
  • You are only answering a conceptual question and no code change is planned.
  • You only need repo-wide text search; use find_code.
PARAMETERS
NameTypeRequiredDescription
pathstringYesAbsolute path to the project root.
taskstringYesPlain-English description of the task you want to do.
DETAILS

PATH PARAMETER

About the path parameter

Use the absolute path to the project root on the machine where the code is available. In Cursor, VS Code, or Windsurf that usually means the workspace root you already have open. On a remote dev box, pass the absolute path on that remote machine. If the path does not exist or the service cannot access it, the tool returns an explicit error instead of guessing. Results are best when the folder is a real project root with .git or package.json. Private GitHub repos are not fetched automatically.

CALL THIS FIRST

Why call scope_task first

Most agents waste 60 to 80 percent of their context reading files that do not matter. scope_task acts as a pre-filter: you describe the work in plain English and it returns only the files you actually need, plus utilities to reuse instead of rebuilding. In practice this usually cuts 3 to 8 unnecessary file reads out of a session.

  • Example task: "Add a rate limit to the /api/webhooks endpoint that allows max 10 requests per minute per IP address."
  • Typical return: the webhook route, the shared rate-limit middleware, the Redis client, and the helper that already enforces sliding-window limits elsewhere.
EXAMPLE
tools-call.json
{  "jsonrpc": "2.0",  "id": 8,  "method": "tools/call",  "params": {    "name": "scope_task",    "arguments": {      "path": "/Users/name/projects/zephex",      "task": "Add a rate limit to the /api/webhooks endpoint that allows max 10 requests per minute per IP address"    }  }}
OUTPUT
response.txt
Relevant files:- src/server/webhooks.ts (target route)- src/middleware/rate-limit.ts (existing limiter pattern)- src/lib/redis.ts (shared Redis client)- src/lib/rateLimiter.ts (reusable checkRateLimit helper)Callers at risk: webhook retries, health checksRisk: medium

TOKEN EFFICIENCY

scope_task usually returns about 250 to 600 tokens. Without it, agents often read 4 to 10 files up front, which commonly costs 4,000 to 18,000 tokens before the real work even starts.