Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Feedback boards for product teams: posts, votes, comments, agent work queue, changelog.
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": {
"queueboard": {
"command": "npx",
"args": [
"-y",
"@reneturcios/queueboard",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add queueboard -- npx -y @reneturcios/queueboard mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"queueboard": {
"command": "npx",
"args": [
"-y",
"@reneturcios/queueboard",
"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": {
"queueboard": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/queueboard",
"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 yesterday.
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, Symantec Cloud DLP AIops
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.
Governed Symantec Cloud DLP — 14 MCP tools, read-only with audit.
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.
queueboard is a small local bridge to FeatureJet's hosted MCP server, which runs feedback boards for product teams: people post ideas and requests to a board, vote and comment on them, and the team works the ranked queue, publishes a changelog and watches board analytics.
The bridge holds no feedback data of its own. It serves the upstream server's tool list locally, exactly as captured from the live endpoint, and forwards each tool call upstream, returning the result untouched. Most of the surface writes to the caller's own workspace - boards, posts and comments are created and edited, an agent can claim a post from the work queue, attach evidence and propose a status change for the owner to confirm.
Boards:
list_boards - every board the caller's key can reach. No arguments.get_board - one board by slug. Required: slug.create_board - a new board, created as a draft. Required: name, slug. Optional: description.publish_board - make a board live at its public URL. Required: slug. Off by default upstream; where it is not enabled the owner publishes from the dashboard.unpublish_board - return a board to draft so its public URL stops serving it. Required: slug.Posts, votes and comments:
list_posts - posts on a board, optionally filtered by status, search text q or tag, with limit and offset paging. Required: slug.get_post - one post in full. Required: slug, post_id.create_post - a new post on a board. Required: slug, title. Optional: body, status, tags.update_post - change mutable post fields such as title, body, status, tags, pinned and queue_rank (a null rank un-ranks the post). Required: slug, post_id.delete_post - hide a post through the developer API. Required: slug, post_id.list_votes - vote metadata for a post. Required: slug, post_id.list_comments - comments on a post. Required: slug, post_id.create_comment - comment as the board team, optionally replying via parent_comment_id. Required: slug, post_id, body.Agent work queue:
get_queue - the top unclaimed posts in the owner's curated build order: ranked posts first, then unranked planned posts by votes. Required: slug. Optional: limit.claim_post - atomically claim a post before working on it, so two agents never build the same thing. Required: slug, post_id. Optional: ttl_seconds (default 3600, max 86400) and agent_label.release_post - give a claim back so other agents can pick the post up. Required: slug, post_id.add_evidence - attach implementation evidence that voters see on the post page. Required: slug, post_id, kind (branch, commit, pr, transcript or url) and ref. Optional: label, action_key.propose_status - propose a status change (open, planned, in_progress, shipped or declined) for the board owner to confirm; nothing changes publicly until a human confirms. Required: slug, post_id, status. Optional: note, action_key.Reads:
get_changelog - shipped posts for a board. Required: slug.get_analytics - read-only analytics for a board, optionally for a period. Required: slug.whoami - confirm the caller's key by listing its accessible boards. No arguments.ping - check MCP and FeatureJet API reachability for the caller's key. No arguments.FEATUREJET_MCP_URL (optional) - override the upstream endpoint. Defaults to https://mcp.featurejet.com/mcp. (The override hook is this rebuild's own labelled reconstruction.)FEATUREJET_API_KEY (optional) - when set, every upstream request carries an Authorization: Bearer header. When it is not set, no auth header is sent. (This forwarding is also a labelled reconstruction; the original surface was captured keyless, and the registry record declares the Authorization header as the key carrier.)On the first tool call the client opens a streamable HTTP session with the upstream: a JSON-RPC initialize request (protocolVersion 2025-03-26, clientInfo name queueboard), then a notifications/initialized notification, then the tools/call request carrying the caller's arguments unchanged. When the upstream answers initialize with an Mcp-Session-Id header, that value rides on every later request of the session, which is reused for the life of the process. Replies may arrive as plain JSON or as server-sent events; both are read.
Successful upstream results pass through verbatim, including any isError flag the upstream sets. Failures - a JSON-RPC error, a non-2xx status, an unreadable response, or a request that cannot be completed - come back as an isError result whose text starts with queueboard error: (this rendering is this rebuild's own labelled reconstruction).
Each tool is also a subcommand taking one JSON argument string (omit it for tools that take none):
npx @reneturcios/queueboard list_boards
npx @reneturcios/queueboard get_board '{"slug":"ideas"}' npx @reneturcios/queueboard create_post '{"slug":"ideas","title":"Dark mode"}' npx @reneturcios/queueboard get_queue '{"slug":"ideas"}' npx @reneturcios/queueboard claim_post '{"slug":"ideas","post_id":42}' npx @reneturcios/queueboard --version
Exit codes: 0 on success, 1 on an isError result, 2 on a usage error.
npx -y @reneturcios/queueboard mcp
MCP client config:
{
"mcpServers": { "queueboard": { "command": "npx", "args": ["-y", "@reneturcios/queueboard", "mcp"] } } }
docker run -i ghcr.io/cloudcorprecords/queueboard
docker run --rm ghcr.io/cloudcorprecords/queueboard --version
The container's default command is mcp, so the first form is a stdio MCP server; any other arguments reach the CLI normally.
npm install
npm run build npm test npm run dev
The test suite runs entirely against a stubbed JSON-RPC upstream - no live network calls.
MIT - see LICENSE.