Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Schedule agent work and report write-once outcomes via CueAPI from any MCP host.
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.
CUEAPI_API_KEY, CUEAPI_BASE_URLValues 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": {
"cueapi": {
"command": "npx",
"args": [
"-y",
"@cueapi/mcp"
],
"env": {
"CUEAPI_API_KEY": "your-value",
"CUEAPI_BASE_URL": "your-value"
}
}
}
}Run this in your terminal
claude mcp add cueapi --env CUEAPI_API_KEY=your-value --env CUEAPI_BASE_URL=your-value -- npx -y @cueapi/mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"cueapi": {
"command": "npx",
"args": [
"-y",
"@cueapi/mcp"
],
"env": {
"CUEAPI_API_KEY": "your-value",
"CUEAPI_BASE_URL": "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": {
"cueapi": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@cueapi/mcp"
],
"env": {
"CUEAPI_API_KEY": "your-value",
"CUEAPI_BASE_URL": "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.
CUEAPI_BASE_URL 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 6, 2026
The registry name was verified against the domain cueapi.ai (the registry checks domain ownership)
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: CUEAPI_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 (0.1.3) reached the registry 7 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, yontu
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.
Türkçe yazı denetimi: TDK kuralları, yapay zekâ izleri, metin türüne göre üslup.
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.
Official Model Context Protocol server for CueAPI, the open-source coordination layer for AI agent systems.
Give your MCP-enabled assistant (Claude Desktop, Cursor, Zed, or any other MCP host) the ability to schedule agent work, fetch execution history, and close the loop with evidence-backed outcome reports, all from inside a conversation.
Agents don't finish in one call. They coordinate across time, tools, environments, agents, and humans. Every handoff is a place where silent failure hides. CueAPI closes each handoff with structured evidence: an external ID, a result URL, or an artifact. This MCP server gives the agent direct access to that surface, so the agent can both schedule its own follow-up work and report outcomes with proof.
npm install -g @cueapi/mcp
npx -y @cueapi/mcp
Add this to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": { "cueapi": { "command": "npx", "args": ["-y", "@cueapi/mcp"], "env": { "CUEAPI_API_KEY": "cue_sk_..." } } } }
Generate your API key at cueapi.ai. Self-hosting? Set CUEAPI_BASE_URL alongside CUEAPI_API_KEY.
Any MCP host that supports stdio servers can run this. Point the host at the cueapi-mcp binary and pass CUEAPI_API_KEY in the environment.
| Tool | What it does |
|---|---|
cueapi_create_cue | Create a recurring (cron) or one-time (at) cue |
cueapi_list_cues | List cues, filter by status |
cueapi_get_cue | Fetch details for a single cue |
cueapi_fire_cue | Fire an existing cue immediately, optional payload override |
cueapi_update_cue | Update a cue's mutable fields (name, schedule, callback, payload, etc.) |
cueapi_pause_cue | Pause a cue so it stops firing |
cueapi_resume_cue | Resume a paused cue |
cueapi_delete_cue | Delete a cue permanently |
cueapi_list_executions | List historical executions, filter by cue/status |
cueapi_get_execution | Fetch a single execution by ID, with state + outcome |
cueapi_list_claimable_executions | List unclaimed worker executions, filter server-side by task/agent |
cueapi_claim_execution | Atomically claim a specific execution for processing |
cueapi_claim_next_execution | Claim the next available execution (optional task filter) |
cueapi_execution_heartbeat | Extend the claim lease on an in-flight execution |
cueapi_report_outcome | Report write-once outcome with evidence (external ID / URL) |
You: Schedule a daily 9am job that posts a digest to my webhook.
Assistant (uses `cueapi_create_cue`): Created cue
cue_abc123, first fire tomorrow at 9:00 UTC.
You: Show me the last five times it ran.
Assistant (uses `cueapi_list_executions`): ...
npm install
npm test # vitest smoke tests for the tool surface npm run build # compile TypeScript to dist/ npm run dev # run the server locally with tsx
cueapi_update_cue tool: update a cue's mutable fields (name, schedule, callback URL, timezone, payload, description). Wraps PATCH /v1/cues/{id}. Sparse update — only provided fields are sent. Closes the cross-wrapper parity gap (every other client wrapper exposed update; MCP didn't until now).cueapi_get_execution, cueapi_list_claimable_executions, cueapi_claim_execution, cueapi_claim_next_execution, cueapi_execution_heartbeat. Closes the receive-claim-process-complete loop for MCP-host agents that want to consume worker-transport executions from in-session (e.g. Claude Desktop, Cursor, Zed). Highlights: list_claimable_executions filters server-side via task / agent query params (client-side filtering hits a known LIMIT-50 starvation bug); claim_next_execution accepts an optional task_name and internally fans out (filtered list → pick oldest → claim by ID) since the server doesn't yet support a task filter on the bare claim endpoint; execution_heartbeat sends worker_id via the X-Worker-Id request header (the server's transport for that field) and requires it in the schema so misconfigured callers fail at the wrapper instead of silently bypassing race protection. Internal: CueAPIClient.request() gains an optional extraHeaders parameter to support per-call custom headers.cueapi_fire_cue tool: fire an existing cue immediately with an optional payload_override (and merge_strategy: 'merge' | 'replace', default 'merge'). Wraps POST /v1/cues/{id}/fire. Lets agents trigger ad-hoc one-shot executions without creating throwaway cues, and lets per-fire dynamic data flow through to webhook dispatch + worker-claim responses without mutating the stored cue.cueapi_pause_cue / cueapi_resume_cue to use PATCH /v1/cues/{id} with {"status": "paused" | "active"} (previously called non-existent /pause and /resume endpoints, returning a runtime 404). PR #1. This is the release that actually contains the fix; 0.1.3 was published prematurely with this note but without the merged code.MIT © Vector Apps Inc.