Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
The open-source review layer for AI agents. Work done for humans is decided by humans.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
GATEWERK_API_KEY, GATEWERK_URL, GATEWERK_REVIEWERValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"gatewerk": {
"command": "npx",
"args": [
"-y",
"@gatewerk/mcp"
],
"env": {
"GATEWERK_API_KEY": "your-value",
"GATEWERK_URL": "your-value",
"GATEWERK_REVIEWER": "your-value"
}
}
}
}Run this in your terminal
claude mcp add gatewerk --env GATEWERK_API_KEY=your-value --env GATEWERK_URL=your-value --env GATEWERK_REVIEWER=your-value -- npx -y @gatewerk/mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"gatewerk": {
"command": "npx",
"args": [
"-y",
"@gatewerk/mcp"
],
"env": {
"GATEWERK_API_KEY": "your-value",
"GATEWERK_URL": "your-value",
"GATEWERK_REVIEWER": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"gatewerk": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@gatewerk/mcp"
],
"env": {
"GATEWERK_API_KEY": "your-value",
"GATEWERK_URL": "your-value",
"GATEWERK_REVIEWER": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
GATEWERK_URL envGATEWERK_REVIEWER envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account gatewerk, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: GATEWERK_API_KEY
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (1.1.4) reached the registry 3 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, AvaHR
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Read hiring data and create inactive assessment and questionnaire drafts for human review.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
The Gatewerk MCP server lets AI agents read and decide reviews from inside Claude Desktop, Claude Code, Cursor, Windsurf, or any Model Context Protocol client. It exposes Gatewerk's review/template/feedback/audit/chain/note APIs as MCP tools, scoped to whatever permissions the API key carries.
Gatewerk is an open-source, self-hosted review layer for AI agents. Work done for humans is decided by humans.
npx @gatewerk/mcp init
The init command prompts for your Gatewerk URL, API key, and (optionally) reviewer email, then prints a config block you paste into your MCP client's settings.
You can also write the config by hand:
{
"mcpServers": { "gatewerk": { "command": "npx", "args": ["-y", "@gatewerk/mcp@1.1.0"], "env": { "GATEWERK_URL": "https://api.gatewerk.com", "GATEWERK_API_KEY": "gwk_...", "GATEWERK_REVIEWER": "alice@team.com" } } } }
GATEWERK_REVIEWER is optional — when set, decisions made through the MCP server are attributed to that reviewer. Otherwise the API key's identity is used.
Tools are filtered automatically based on the scopes attached to your API key. A key with only reviews:read will not see gatewerk_decide_review.
gatewerk_create_review — submit a new review request (scope: reviews:create)gatewerk_list_reviews — list reviews with filters (scope: reviews:read)gatewerk_get_review — fetch a review with its template metadata (scope: reviews:read)gatewerk_decide_review — approve / reject / edit / retry a review [deprecated; prefer gatewerk_take_review_action] (scope: reviews:decide)gatewerk_take_review_action — invoke a configurable action on a review; supports built-in and template-specific action IDs (scope: reviews:decide)gatewerk_list_review_actions — introspect the available actions on a review's template (scope: reviews:read)gatewerk_list_templates — list templates (scope: templates:read)gatewerk_create_template — define a template (scope: templates:write)gatewerk_update_template — modify a template (scope: templates:write)gatewerk_delete_template — remove a template (scope: templates:write)gatewerk_start_chain_run — start a multi-step review chain from a definition (scope: templates:write)gatewerk_get_chain_run — fetch a chain run + steps by ID (scope: reviews:read)gatewerk_get_chain_for_review — get chain context for a review (scope: reviews:read)gatewerk_create_note — post a note, optionally pinned to one or more reviews/templates/chain runs (scope: notes:write)gatewerk_list_notes — list notes with filters (author, tags, target, shared/private) (scope: notes:read)gatewerk_query_feedback — query past decisions for learning (scope: feedback:read)gatewerk_query_audit — query the audit trail (scope: audit:read)gatewerk_get_stats — review metrics + daily trend (scope: stats:read)You'll need a Gatewerk API key with the appropriate scopes. Generate one at:
/settings/api-keys pageCommon scope bundles:
reviews:create, feedback:readreviews:read, reviews:decide, templates:read, notes:read, notes:write| Variable | Required | Description |
|---|---|---|
GATEWERK_API_KEY | yes | API key (gwk_...) |
GATEWERK_URL | no | Gatewerk base URL (defaults to http://localhost:3100) |
GATEWERK_REVIEWER | no | Reviewer email used as decision attribution |