Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Validate dashboard setup files and widget endpoint responses against the dashboardbase contract.
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.
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": {
"dashcheck": {
"command": "npx",
"args": [
"-y",
"@reneturcios/dashcheck",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add dashcheck -- npx -y @reneturcios/dashcheck mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"dashcheck": {
"command": "npx",
"args": [
"-y",
"@reneturcios/dashcheck",
"mcp"
]
}
}
}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": {
"dashcheck": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/dashcheck",
"mcp"
]
}
}
}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.
These 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 6, 2026
The registry name was verified with the GitHub account CloudCorpRecords, 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.
The registry does not list a required key, though some servers ask you to sign in on first use.
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 (0.1.0) reached the registry 2 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js, Docker on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, LickityClick
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.
Create, edit and track LickityClick short links, campaigns and click stats from your AI assistant.
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.
Check a dashboard before you ship it. dashcheck is a small client for the dashboardbase validation service: hand it a setup file and it reports any schema, layout, binding or contents errors; hand it the JSON a widget endpoint actually returned and it checks that body against the widget contract for its type; and when a setup is ready to share, it can mint a read-only link to it that expires after 48 hours.
Setup content can be passed inline as a string or pointed at with a local file path — in the path case the file is read on your machine and its text is what gets sent. Whatever the service returns comes back exactly as it sent it: nothing is trimmed, renamed or summarised on the way through. That includes refusals: if a setup file carries credentials, the service itself refuses to create a link and lists the offending fields, and that refusal body passes through like any other response.
Three environment variables control the client:
DASHBOARDBASE_API_URL (optional) — API base URL. Defaults to https://api.dashboardbase.com.DASHBOARDBASE_API_KEY (optional) — when set, it is sent on every request as the x-api-key header. Leaving it unset is not an error: the validation endpoints are usable without a key.DASHBOARDBASE_TIMEOUT_MS (optional) — request timeout in milliseconds, enforced with an abort controller. Defaults to 15000; a timeout counts as a fetch failure.validate_setup_file — validate a dashboardbase setup file (JSON) and return any schema, layout, binding, or contents errors. Takes content (the setup file contents) or path (a local path to a setup file); one of them is required.validate_widget_response — validate a widget endpoint's JSON response against the dashboardbase widget contract for its type (kpi, timeseries, bar, table or text). Takes response (the JSON body the endpoint returned) or path (a local path to a JSON file holding the response); one of them is required. widgetType is optional and overrides the type field in the response envelope. A response value that parses as JSON is sent as the parsed value; otherwise it is sent as the raw string.create_setup_link — create a shareable, read-only setup link for a setup file; the link expires after 48 hours. Takes content or path, as above.The one-of rule is enforced locally before any request: one of content or path is required (for the widget-response tool, one of response or path is required). A local file that cannot be read fails with cannot read file: . An upstream non-2xx reply fails with dashboardbase error: HTTP and an unreachable API (including a timeout) with dashboardbase unreachable.
The original record pins the three tools, their argument tables, the three environment variables, the 48-hour link behaviour and the credential-refusal behaviour, but it does not publish the upstream HTTP paths. The three paths below are reconstructions, labelled as such:
POST /validate/setup-file with JSON body {"content": "..."} — reconstruction (used by validate_setup_file).POST /validate/widget-response with JSON body {"response": ..., "widgetType": "..."} (the widgetType key is omitted when not given) — reconstruction (used by validate_widget_response).POST /setup-links with JSON body {"content": "..."} — reconstruction (used by create_setup_link).Each tool is a subcommand taking one JSON argument string:
npx @reneturcios/dashcheck validate_setup_file '{"path":"./setup.json"}'
npx @reneturcios/dashcheck validate_widget_response '{"response":"{\"type\":\"kpi\",\"value\":42}","widgetType":"kpi"}' npx @reneturcios/dashcheck create_setup_link '{"content":"{\"widgets\":[]}"}' npx @reneturcios/dashcheck --version
Output is the tool's result text (the upstream body on success). Exit codes: 0 on success, 1 on a runtime error (including a validation, file-read or upstream failure), 2 on a usage error.
npx -y @reneturcios/dashcheck mcp
MCP client config (the key is optional; provide it through the client's environment when you have one):
{
"mcpServers": { "dashcheck": { "command": "npx", "args": ["-y", "@reneturcios/dashcheck", "mcp"], "env": { "DASHBOARDBASE_API_KEY": " " } } } }
docker run -i ghcr.io/cloudcorprecords/dashcheck
docker run --rm ghcr.io/cloudcorprecords/dashcheck validate_setup_file '{"path":"./setup.json"}'
npm install
npm run build # tsc -> dist/ npm test # tsx --test test/*.test.ts (fake fetch and injected file reader only, no network) npm run dev # run the CLI from source
MIT — Copyright (c) 2026 Rene Turcios