specpack MCP Server

by the-kipdev Your server? Claim it

answering

specpack is answering right now. Last checked 2 min ago. 168 installs a week from npm. It exposes 5 tools. Last commit 18 Sep 2026.

Audit and write CLAUDE.md / AGENTS.md / Cursor rules; generate full build specs for new projects.

Installs per day peak 120 · avg 4

a month agotoday

Uptime history 4 days of history

4 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

284 ms

Response time

average over 24h

168

Installs / week

npm and PyPI

Nothing serious here today

Today is the operative word: we check specpack every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add specpack --transport http https://prompt-generator-website.com/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "specpack": {
      "url": "https://prompt-generator-website.com/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.specpack]
url = "https://prompt-generator-website.com/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "specpack": {
      "url": "https://prompt-generator-website.com/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "specpack": {
      "url": "https://prompt-generator-website.com/mcp"
    }
  }
}

This one needs environment variables set before it will start: SPECPACK_API_KEY (Optional prompt-generator-website.com API key (pgw_…): more specs and AI drafts than the free quota.). The author declared them in the registry entry; get the values from the project itself.

Available tools 5

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

draft

draft_answers

Asks the server's AI (Claude) to fill the whole questionnaire from a plain-language project description; returns the project type, the answers and the assumptions it made. Takes 10-40 s and consumes one AI draft (3 free without an API key). Prefer answering get_questionnaire yourself when you already know the project; use this when you only have a one-line idea. Review the assumptions with the user before calling generate_spec.

generate

generate_spec

Turns questionnaire answers into a complete build specification (stack, database schema, auth flows, pages, design system, SEO, security, legal, deployment, file structure) and the matching agent files. Deterministic: the same answers always give the same bytes. Values: select/radio = one option value, multiselect = array of option values, boolean = true/false, number = number. Returns the requested files; by default AGENTS.md (full spec + working agreement) and CLAUDE.md (imports AGENTS.md) — write them at the repository root. Uses one spec from the quota (2 free without an API key).

project

list_project_types

The project types the spec generator knows (saas, ecommerce, business, marketplace, blog, webapp, landing), with what each covers.

questionnaire

get_questionnaire

The questions for one project type: universal questions first, then type-specific ones. Each has an id, a type (text, textarea, select, radio, multiselect, boolean, number), options where relevant, and sometimes a condition (ask it only when another answer matches). Answer from what you know of the project, then pass the answers to generate_spec. Only project_name and project_description are required; skipped questions fall back to defaults.

usage

get_usage

Current plan and quota usage (specs and AI drafts) for the API key, or for this address when no key is set.

Endpoints

URL	Transport	State	Latency	Checked
https://prompt-generator-website.com/mcp	streamable-http	answering	507 ms	2 min ago

Alternatives to specpack

same job, measured the same way

Promptarch

by promptarch

Research-backed linting + generation for agent context files (CLAUDE.md, AGENTS.md, Cursor rules).

3 tools answering

MaShop MCP

by mashop

Build, deploy and manage MaShop e-commerce projects from Claude, Cursor or any MCP client.

answering

Agentcontext

by mbeato

Normalize AGENTS.md / CLAUDE.md / .cursor/rules / .clinerules / .windsurf/rules from one source.

28 installs/wk local only

Rules-Generator-Pro

by evozim

Automated .cursorrules and system prompt generator.

answering

Genexus

by lennix1337

Read, edit, and analyze GeneXus 18 KB objects from Claude, Cursor, and AI agents.

2 034 installs/wk local only

Context Autopilot

by chiragbachani

Mines your Claude Code and Cursor sessions into evidence-based CLAUDE.md / AGENTS.md rules.

56 installs/wk local only

AI Agent Search Optimization

by seyitkaangunes

Audit AI search readiness, generate llms.txt drafts, and build GEO/AEO prompt matrices for websites.

27 installs/wk local only

Clipia

by clipia-ai

Generate AI images, video, speech, music and presentations from Claude, ChatGPT and Cursor.

answering

specpack — questions

Answers built from our own checks of this server.

What can specpack do?

It exposes 5 tools, read directly from the server on our last check. Among them: draft_answers, generate_spec, get_questionnaire, get_usage, list_project_types. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is specpack working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 284 ms. The bar chart above shows every period we have measured.

How do I connect specpack?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does specpack need an API key?

No. specpack completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 5 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is specpack?

It answers our handshake in 284 ms on average, which is faster than 55% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

How many people use specpack?

The npm package specpack was installed 168 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is specpack open source?

Yes — it is published under the MIT licence, written in TypeScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.