Add Zephex in Settings → Tools → AI Assistant → Model Context Protocol (MCP). Choose HTTP / Streamable HTTP (not STDIO) and point to https://zephex.dev/mcp with Bearer authentication.
Official JetBrains AI Assistant MCP documentation: JetBrains AI Assistant MCP docs
Without MCP, your agent guesses project layout and misses supply-chain risk. Zephex connects one hosted endpoint so every session gets the same ten tools — no per-machine npm installs, no version drift across the team.
HTTP and stdio setups both need a key from your Zephex dashboard. OAuth-only flows (ChatGPT, Claude.ai web) sign you in in the browser instead — skip this section for those.
Matches the published CLI (mcp-proxy/src/commands/setup.ts). One command signs you in, writes the correct transport, and verifies 10 tools.
Account teardown: logout vs disconnect · Connect MCP walkthrough
Search docs for “where is my MCP file” — the answer is always: run list first, then open the path it prints.
Documented paths: <project>/.junie/mcp/mcp.json
JetBrains/Junie MCP is stdio-only per vendor docs; wizard writes npx zephex.
Runs the same code as mcp-proxy/src/commands/setup.ts — OAuth in browser, creates a CLI key, writes your editor config, verifies tools.
npx -y zephex setup --jetbrainsSkip browser OAuth — paste a key from zephex.dev/dashboard/keys. Must start with mcp_prod_, mcp_dev_, or mcp_sk_.
npx -y zephex setup --jetbrains --api-key mcp_prod_your-key-hereIf you edit by hand after setup: Transport: stdio (see <project>/.junie/mcp/mcp.json).
{ "mcpServers": { "zephex": { "command": "npx", "args": ["-y", "zephex"], "env": { "ZEPHEX_API_KEY": "mcp_sk_your_key_here" } } }}After CLI install, fully restart the app if tools do not appear. Manual JSON/TOML blocks below are equivalent — use them when CLI commands are unavailable.
Full comparison: HTTP vs stdio · npx zephex reference
In Settings → AI Assistant → MCP, pick HTTP / Streamable HTTP (not STDIO). Paste JSON or use the form; click Apply to spawn the connection.
Replace mcp_sk_your_key_here with your key from Dashboard → API Keys. Copy the full key once at creation — paste into Authorization: Bearer … for HTTP configs, or into ZEPHEX_API_KEY for stdio/npx configs.
JetBrains Streamable HTTP — mcpServers with url (and headers when available).
{ "mcpServers": { "zephex": { "url": "https://zephex.dev/mcp", "headers": { "Authorization": "Bearer mcp_sk_your_key_here" } } }}Tip
Import from Claude only if you want other servers — add Zephex as a separate HTTP entry.
Note
If your IDE build only accepts url without headers in JSON, add the Bearer token in the MCP server's auth/header UI field if shown.
Run these in a terminal when the editor UI is unclear — catches stale npm, wrong transport, and project shadows.
npx -y zephex@latest listnpx -y zephex@latest doctornpx -y zephex@latest repair# Fully quit the editor (Cmd+Q / Alt+F4), reopen, start a new agent sessionAfter saving your config, confirm Zephex is connected before you rely on it in real work.
Questions people ask when JetBrains AI Assistant does not show Zephex tools — indexed for docs search.
How do I connect Zephex to jetbrains?
Fastest: npx -y zephex setup --jetbrains (browser sign-in, writes config, verifies 10 tools). Or paste manual config on this page, save, fully quit the app, reopen.
Where did setup save my jetbrains MCP config?
Run npx -y zephex@latest list — it prints every config path on this machine that references Zephex.
jetbrains works in terminal but not in the editor
GUI apps often lack nvm/fnm PATH. Run npx -y zephex@latest repair, ensure Node is on system PATH, fully quit the editor.
How do I disconnect Zephex from jetbrains?
mcpcli disconnect --jetbrains — revokes key and strips config.
You do not call tools yourself — ask your agent in plain language. Try these once Zephex is connected:
“AI Assistant chat: get_project_context on the IntelliJ project path for this module.”
Streamable HTTP MCP from Settings — tools in the / command list.
“find_code @SpringBootApplication and read_code the security filter chain config.”
Java/Kotlin navigation via MCP instead of manual structure search.
“check_test: extract payment logic into a new Gradle module.”
Multi-module scope with risk notes for refactor.
“check_package on a Maven coordinate a stackoverflow answer suggested.”
Verify before adding to pom.xml or build.gradle.kts.
“explain_architecture for our Spring Cloud gateway and downstream services.”
Mermaid for microservice boundaries.
“audit_headers on the URL where our Spring Boot app is deployed.”
Production header grade from the IDE chat.
Invoke tools from AI Assistant chat with / commands or natural language. Pass module or project path for multi-module Gradle/Maven trees.
These situations usually mean the setup cannot work until you fix the underlying issue:
Connection failed
HTTP transport, URL https://zephex.dev/mcp.
No auth field
Paste headers in JSON or IDE auth UI.
STDIO timeout
Switch from npx stdio to HTTP url.
Tools grayed out
Enable checkbox and click Apply.
Wrong module
Pass projectPath or github: in prompt.
HTTP MCP blocked by enterprise policy
Ask IT to allow outbound HTTPS to zephex.dev/mcp for the IDE, or use a team-approved proxy.
Tools list empty after green status
Open AI chat, type / for MCP tools, ensure zephex server checkbox is enabled.
JetBrains AI Assistant Streamable HTTP — ten tools in MCP settings:
get_project_context
Reads your project structure, dependencies, scripts, env vars, and framework markers in one call. Replaces manually opening package.json, tsconfig, and multiple config files at the start of every session.
read_code
AST-based code extraction: pass a symbol name and get the implementation without reading entire files. Supports symbol lookup, batched file reads, and structural outlines for large files.
find_code
Ranked search across the repo for definitions, usages, and patterns. Faster than blind grep when the agent does not know where a symbol lives.
check_package
Live registry lookup for npm, PyPI, Cargo, and Go modules. Surfaces typosquat risk, maintainer changes, and suspicious version jumps before you run install.
explain_architecture
Generates Mermaid diagrams for auth flows, service boundaries, and module dependencies so the agent reasons about structure instead of guessing.
check_test
Turns a task description into the smallest file set to read or edit, with risk ratings and caller impact notes.
audit_headers
Grades a deployed URL for CSP, HSTS, TLS, cookies, and redirects. Returns fix snippets for common hosts (Vercel, Cloudflare, Nginx).
keep_thinking
Structured multi-step debugging: tracks hypotheses and conclusions so long investigations do not loop.
Zephex_dev_info
Expert patterns for authentication, databases, frontend frameworks, deployment, and mobile stacks when the agent needs vetted guidance.
project_memory
Persists decisions, gotchas, and conventions per project in ~/.zephex/memory (SQLite FTS5). recall before unfamiliar areas; remember after discoveries. Local stdio only on npx zephex.