Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Beck agent plan board: workspaces, documents, epics, tasks, decisions and progress over REST.
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": {
"planboard": {
"command": "npx",
"args": [
"-y",
"@reneturcios/planboard",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add planboard -- npx -y @reneturcios/planboard mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"planboard": {
"command": "npx",
"args": [
"-y",
"@reneturcios/planboard",
"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": {
"planboard": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/planboard",
"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 3 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, Safe Fetch
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.
MCP server for fetching URLs, safe against SSRF, DNS rebinding, and redirect-to-internal attacks.
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.
A small client for the Beck agent plan board. Beck keeps the shared state an agent team works from — workspaces, planning documents, epics, tasks, progress checks and open decisions — behind a REST API, and planboard exposes that API as 34 MCP tools plus a matching command line, so an agent (or a human at a terminal) can read the board, move tasks along, guard document edits with etags, and answer the decisions that block work.
whoami, list_workspaces, create_workspace.list_api_tokens, create_api_token, revoke_api_token.list_documents, read_document, create_document, write_document, delete_document, list_document_versions, restore_document. Writes and deletes are guarded by the document's etag, sent as an If-Match header, so a stale editor cannot silently overwrite someone else's revision.list_epics, get_epic, plan_it, get_epic_github, link_epic_github.list_tasks (filterable by status, epic, assignee and icebox), get_task, get_task_context, recommend_task, start_task, finish_task (with a what-was-attempted report), accept_task, reject_task (a reason is required), update_task (only the fields you provide are sent), add_comment, list_comments.log_progress (passed/total checks with an optional note and label) and list_progress.list_decisions (filterable by open / answered status and epic), ask_decision (every question carries a default answer), and answer_decision, which accepts exactly one of an explicit answer or keepDefault: true.Workspace scoping is explicit everywhere: every workspace-scoped tool takes a required workspaceId, sent as a query parameter on reads and deletes and inside the JSON body on writes.
export BECK_API_TOKEN="..." # required
export BECK_API_URL="https://beck.bot" # optional override export BECK_REPO="owner/repo" # optional, sent as X-Beck-Repo export BECK_BRANCH="main" # optional, sent as X-Beck-Branch
Without BECK_API_TOKEN, every tool returns the error text BECK_API_TOKEN is not set and no request is made. Each process also generates one random run id, sent as X-Beck-Run on every request, so the server can group the calls a single agent run makes. The token itself never appears in any tool output.
Successful calls return the upstream JSON body, pretty-printed. A non-2xx response becomes an error result of the form upstream error: HTTP from beck-api, with : appended when the response body carries a message or error string; a request that never completes becomes upstream unreachable: beck-api.
Each tool is a subcommand taking one JSON argument string:
npx @reneturcios/planboard whoami '{}'
npx @reneturcios/planboard list_tasks '{"workspaceId":"w1","status":"open"}' npx @reneturcios/planboard write_document '{"workspaceId":"w1","path":"plan.md","content":"...","etag":"etag-7"}' npx @reneturcios/planboard answer_decision '{"workspaceId":"w1","decisionId":"d1","keepDefault":true}' npx @reneturcios/planboard --version
Output is the same text the MCP tool returns. Exit codes: 0 on success, 1 when the tool result is an error, 2 on a usage error.
npx -y @reneturcios/planboard mcp
MCP client config:
{
"mcpServers": { "planboard": { "command": "npx", "args": ["-y", "@reneturcios/planboard", "mcp"], "env": { "BECK_API_TOKEN": "..." } } } }
docker run -i -e BECK_API_TOKEN="..." ghcr.io/cloudcorprecords/planboard
docker run --rm -e BECK_API_TOKEN="..." ghcr.io/cloudcorprecords/planboard list_epics '{"workspaceId":"w1"}'
npm install
npm run build # tsc -> dist/ npm test # tsx --test test/*.test.ts (fake fetch only, no network) npm run dev # run the CLI from source
MIT — Copyright (c) 2026 Rene Turcios