Learn
Straight answers for developers setting up a hosted MCP server in Cursor, Claude Code, or VS Code. No fluff—each section starts with the short answer, then steps or links if you need more.
Solo builders on Cursor/Claude Code who need real repo context; teams rolling out MCP across editors with one API key policy; and security-minded engineers who want check_package before every npm install. Not for chat memory (Mem0) or docs-only MCP (Context7) — though many teams use both alongside Zephex.
Zephex is a hosted MCP server for AI coding tools. You connect Cursor, Claude Code, VS Code, or other MCP editors with one API key and get ten built-in tools: project overview, code search, package safety checks, architecture diagrams, and more.
Local MCP runs small programs on your laptop—private and fast, but you set them up again for every editor and every teammate. Hosted MCP (Zephex) gives everyone the same tools through one key and one endpoint, with package audits and usage tracking built in.
You need a Zephex API key and a small JSON file in your project. After that, restart Cursor once and check that ten tools show up.
Claude Code reads MCP settings from your user config file. Add Zephex there, restart the app, and check /mcp.
VS Code can talk to Zephex over HTTPS. You put the endpoint in `.vscode/mcp.json` and paste your API key when prompted.
Most people finish in about two minutes: one API key, one config file, one editor restart. You do not install a separate MCP server repo on each machine.
Free is 555 requests per month per account (all keys share one quota). Pro is 3,500 for $7/month. Max is 10,000 for $19/month. Each tool call counts as one request. If you go over the limit, share your link for +300 bonus requests or upgrade.
Context7 pulls fresh documentation for libraries (great for “how does this API work?”). Zephex works on your actual project: your files, your dependencies, your folder structure. Lots of teams use both.
No. Mem0-style tools remember chat facts over time (preferences, notes). Zephex helps the agent understand the codebase you have open right now—search code, audit packages, map architecture. Different jobs.
No. Zephex does not clone GitHub for you. Tools read files on the machine where your editor is running. If the repo is checked out locally, the agent can analyze it.
No. We do not use your code, prompts, or tool output to train models. Data is used only to answer the current tool call, then discarded. Details are on our Data Use and Security pages.
Use check_package before you run npm install. It checks the live registry for typosquats and red flags. For big version jumps, use check_package with task=upgrade or task=security for CVEs and breaking changes.
Yes. check_package with task=upgrade shows breaking changes between versions. check_test lists which files will need edits. That is the same idea as catching a fake Stripe package before install—verify first, then change code.
Run get_project_context first (stack, scripts, key paths). Then explain_architecture for a diagram. Then find_code or read_code on the files the agent actually needs—instead of opening fifty files by hand.
Use one hosted endpoint and the same editor guides for everyone. Give each environment its own API key if you want (staging vs prod). Track usage in the dashboard.
Yes. VS Code often uses HTTP to https://zephex.dev/mcp with a Bearer key. Cursor and Claude Code usually use stdio via `npx zephex`, which still talks to our hosted backend. See the OAuth & HTTP doc for your editor.
You get HTTP 429 with Retry-After. Upgrade your plan, wait for the monthly reset, or slow down tool calls. Tell the agent to stop retrying in a loop when you see the limit.
Ten tools: get_project_context, read_code, find_code, check_package, check_test, project_memory, explain_architecture, audit_headers, keep_thinking, and Zephex_dev_info.
Yes. We document Windsurf MCP setup the same way as Cursor—global config path plus your API key.
Depends what you need. For library docs only, try a docs MCP like Context7. For your real repo, package audits, and one config for the whole team, Zephex is built for that—ten tools, one key.
Usually the config file is in the wrong folder, JSON has a typo, or Cursor was only reloaded—not fully quit. Put `.cursor/mcp.json` in the project root, fix JSON, quit with Cmd+Q, reopen, new chat.
Yes. https://zephex.dev/llms.txt lists tools, editors, and the best doc links. Agents can start there instead of guessing URLs.
Filesystem MCP only reads local files. Zephex adds package registry checks, AST-aware code tools, and one setup for every editor on the team.
GitHub MCP automates issues, PRs, and GitHub API actions across org repos. Zephex analyzes your checked-out codebase — AST search, package audits, architecture maps. Use both: GitHub MCP for collaboration on GitHub.com, Zephex for private monorepo work on disk.
For your real repo and npm safety: Zephex — ten tools, one ~/.claude.json entry, package audits built in. For GitHub issues and PRs: GitHub MCP. For library docs: Context7. Most Claude Code power users run Zephex daily and add niche servers only when needed.
Before npm install, call Zephex check_package on the package name — it checks the live registry for typosquats, version status, and red flags. For upgrades use task=upgrade; for CVEs use task=security. Use project_memory to remember decisions, gotchas, and goals across sessions via local SQLite (stdio only).
check_package docs · Package safety workflow · Why not GitHub MCP alone
Smithery helps you discover and install individual MCP servers. Zephex is one hosted server with ten engineering tools already bundled — no marketplace assembly. Use both if you want niche servers plus a core codebase toolkit.
Yes. Run npx zephex in your terminal for get-context, find-code, check-package, and more — same backend as MCP, human-readable output. Try the live demo at /cli.
Contact support for higher limits, SLAs, or custom terms. Most small teams use Free, Pro, or Max on the pricing page.
Revoke it in the dashboard immediately and create a new key. Update every editor config that used the old key.
Google’s MCP servers connect to BigQuery, Firebase, and other Google data with IAM. Zephex is for everyday app development on any stack—your code, your npm packages, any editor.
When debugging is stuck after the first fix. It keeps track of what you tried, what failed, and what you learned—so the agent does not loop on the same bad guess.
Yes—explain_architecture outputs Mermaid diagrams (auth, services, dependencies). Run get_project_context first so the agent knows your stack.
https://zephex.dev/changelog — dated releases for tools, editors, and platform changes.
Learn
Straight answers for developers setting up a hosted MCP server in Cursor, Claude Code, or VS Code. No fluff—each section starts with the short answer, then steps or links if you need more.
Solo builders on Cursor/Claude Code who need real repo context; teams rolling out MCP across editors with one API key policy; and security-minded engineers who want check_package before every npm install. Not for chat memory (Mem0) or docs-only MCP (Context7) — though many teams use both alongside Zephex.
Zephex is a hosted MCP server for AI coding tools. You connect Cursor, Claude Code, VS Code, or other MCP editors with one API key and get ten built-in tools: project overview, code search, package safety checks, architecture diagrams, and more.
Local MCP runs small programs on your laptop—private and fast, but you set them up again for every editor and every teammate. Hosted MCP (Zephex) gives everyone the same tools through one key and one endpoint, with package audits and usage tracking built in.
You need a Zephex API key and a small JSON file in your project. After that, restart Cursor once and check that ten tools show up.
Claude Code reads MCP settings from your user config file. Add Zephex there, restart the app, and check /mcp.
VS Code can talk to Zephex over HTTPS. You put the endpoint in `.vscode/mcp.json` and paste your API key when prompted.
Most people finish in about two minutes: one API key, one config file, one editor restart. You do not install a separate MCP server repo on each machine.
Free is 555 requests per month per account (all keys share one quota). Pro is 3,500 for $7/month. Max is 10,000 for $19/month. Each tool call counts as one request. If you go over the limit, share your link for +300 bonus requests or upgrade.
Context7 pulls fresh documentation for libraries (great for “how does this API work?”). Zephex works on your actual project: your files, your dependencies, your folder structure. Lots of teams use both.
No. Mem0-style tools remember chat facts over time (preferences, notes). Zephex helps the agent understand the codebase you have open right now—search code, audit packages, map architecture. Different jobs.
No. Zephex does not clone GitHub for you. Tools read files on the machine where your editor is running. If the repo is checked out locally, the agent can analyze it.
No. We do not use your code, prompts, or tool output to train models. Data is used only to answer the current tool call, then discarded. Details are on our Data Use and Security pages.
Use check_package before you run npm install. It checks the live registry for typosquats and red flags. For big version jumps, use check_package with task=upgrade or task=security for CVEs and breaking changes.
Yes. check_package with task=upgrade shows breaking changes between versions. check_test lists which files will need edits. That is the same idea as catching a fake Stripe package before install—verify first, then change code.
Run get_project_context first (stack, scripts, key paths). Then explain_architecture for a diagram. Then find_code or read_code on the files the agent actually needs—instead of opening fifty files by hand.
Use one hosted endpoint and the same editor guides for everyone. Give each environment its own API key if you want (staging vs prod). Track usage in the dashboard.
Yes. VS Code often uses HTTP to https://zephex.dev/mcp with a Bearer key. Cursor and Claude Code usually use stdio via `npx zephex`, which still talks to our hosted backend. See the OAuth & HTTP doc for your editor.
You get HTTP 429 with Retry-After. Upgrade your plan, wait for the monthly reset, or slow down tool calls. Tell the agent to stop retrying in a loop when you see the limit.
Ten tools: get_project_context, read_code, find_code, check_package, check_test, project_memory, explain_architecture, audit_headers, keep_thinking, and Zephex_dev_info.
Yes. We document Windsurf MCP setup the same way as Cursor—global config path plus your API key.
Depends what you need. For library docs only, try a docs MCP like Context7. For your real repo, package audits, and one config for the whole team, Zephex is built for that—ten tools, one key.
Usually the config file is in the wrong folder, JSON has a typo, or Cursor was only reloaded—not fully quit. Put `.cursor/mcp.json` in the project root, fix JSON, quit with Cmd+Q, reopen, new chat.
Yes. https://zephex.dev/llms.txt lists tools, editors, and the best doc links. Agents can start there instead of guessing URLs.
Filesystem MCP only reads local files. Zephex adds package registry checks, AST-aware code tools, and one setup for every editor on the team.
GitHub MCP automates issues, PRs, and GitHub API actions across org repos. Zephex analyzes your checked-out codebase — AST search, package audits, architecture maps. Use both: GitHub MCP for collaboration on GitHub.com, Zephex for private monorepo work on disk.
For your real repo and npm safety: Zephex — ten tools, one ~/.claude.json entry, package audits built in. For GitHub issues and PRs: GitHub MCP. For library docs: Context7. Most Claude Code power users run Zephex daily and add niche servers only when needed.
Before npm install, call Zephex check_package on the package name — it checks the live registry for typosquats, version status, and red flags. For upgrades use task=upgrade; for CVEs use task=security. Use project_memory to remember decisions, gotchas, and goals across sessions via local SQLite (stdio only).
check_package docs · Package safety workflow · Why not GitHub MCP alone
Smithery helps you discover and install individual MCP servers. Zephex is one hosted server with ten engineering tools already bundled — no marketplace assembly. Use both if you want niche servers plus a core codebase toolkit.
Yes. Run npx zephex in your terminal for get-context, find-code, check-package, and more — same backend as MCP, human-readable output. Try the live demo at /cli.
Contact support for higher limits, SLAs, or custom terms. Most small teams use Free, Pro, or Max on the pricing page.
Revoke it in the dashboard immediately and create a new key. Update every editor config that used the old key.
Google’s MCP servers connect to BigQuery, Firebase, and other Google data with IAM. Zephex is for everyday app development on any stack—your code, your npm packages, any editor.
When debugging is stuck after the first fix. It keeps track of what you tried, what failed, and what you learned—so the agent does not loop on the same bad guess.
Yes—explain_architecture outputs Mermaid diagrams (auth, services, dependencies). Run get_project_context first so the agent knows your stack.
https://zephex.dev/changelog — dated releases for tools, editors, and platform changes.