Was this page helpful?
Connect Zephex with npx -y zephex setup (top), or context_servers url + Bearer in Zed settings. Hosted https://zephex.dev/mcp is recommended over local npx stdio.
Official Zed MCP documentation: Zed MCP docs
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.
Zed context_servers stdio — not url-only remote.
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 --zedSkip browser OAuth — paste a key from zephex.dev/dashboard/keys. Must start with mcp_prod_, mcp_dev_, or mcp_sk_.
npx -y zephex setup --zed --api-key mcp_prod_your-key-herecontext_servers command/args/env: Transport: stdio (see ~/.config/zed/settings.json).
{ "context_servers": { "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
Zed Agent Panel → Add Custom Server merges into context_servers in settings.json. Include Authorization Bearer so Zed does not start OAuth for Zephex.
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.
context_servers command/args/env per writeZedConfig.
{ "context_servers": { "zephex": { "command": "npx", "args": ["-y", "zephex"], "env": { "ZEPHEX_API_KEY": "mcp_sk_your_key_here" } } }}Manual HTTP; repo tools need github: paths.
{ "context_servers": { "zephex": { "url": "https://zephex.dev/mcp", "headers": { "Authorization": "Bearer mcp_sk_your_key_here" } } }}Tip
If no Authorization header is set, Zed may prompt for OAuth — Zephex uses Bearer; include the header to skip OAuth.
After saving your config, confirm Zephex is connected before you rely on it in real work.
You do not call tools yourself — ask your agent in plain language. Try these once Zephex is connected:
“Zed Agent Panel: get_project_context on the folder open in this window.”
context_servers remote Zephex — green dot means tools are live.
“read_code impl Editor for our custom Zed extension crate.”
Rust symbol read without dumping the crate.
“find_code TreeSitter query definitions in extensions/*.”
Navigate extension codebases faster.
“explain_architecture for LSP ↔ agent tool routing in our fork.”
Diagram before large Zed patches.
“check_package on a wasm-bindgen-related npm helper before install.”
Registry check for hybrid Rust/JS tooling.
“scope_task: add keymap for a new agent command palette action.”
Touches settings, keymaps, and command modules only.
Zed Agent Panel tools respect context_servers config. Mention zephex by name if the model does not pick MCP tools automatically.
These situations usually mean the setup cannot work until you fix the underlying issue:
Inactive server
url + Authorization in context_servers.
OAuth loop
Set Bearer header — Zephex uses API key auth.
0 tools
Remove command-based zephex entry.
Tools filtered
Enable zephex in agent profile tool permissions.
Wrong path
Absolute path or github: in message.
Zed prompts for OAuth instead of Bearer
Include Authorization: Bearer mcp_sk_... in context_servers.zephex headers—Zephex does not use OAuth.
Green indicator but tools never invoked
Start a new agent thread and explicitly ask to use zephex or call check_package.
Zed context_servers — ten tools when the server indicator is green:
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.
audit_package
Deep package intelligence: CVEs with severity, breaking changes between versions, migration notes, and peer-dependency conflicts.
explain_architecture
Generates Mermaid diagrams for auth flows, service boundaries, and module dependencies so the agent reasons about structure instead of guessing.
scope_task
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.