specpack is an MCP server published by io.github.THE-KIPDEV, hosted at prompt-generator-website.com. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 5 tools, including list_project_types, get_questionnaire, generate_spec, draft_answers, get_usage.
Audit and write CLAUDE.md / AGENTS.md / Cursor rules; generate full build specs for new projects.
1 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
The project types the spec generator knows (saas, ecommerce, business, marketplace, blog, webapp, landing), with what each covers.
No parameters.
{
"name": "list_project_types",
"title": "List project types",
"description": "The project types the spec generator knows (saas, ecommerce, business, marketplace, blog, webapp, landing), with what each covers.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}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.
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
| Parameter | Type | Description |
|---|---|---|
| type * | string | Project type id |
{
"name": "get_questionnaire",
"title": "Get the questionnaire",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"saas",
"ecommerce",
"business",
"marketplace",
"blog",
"webapp",
"landing"
],
"type": "string",
"description": "Project type id"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}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).
| Parameter | Type | Description |
|---|---|---|
| type * | string | one of ["saas","ecommerce","business","marketplace","blog","webapp","landing"] |
| files | array | Files to return. Default: ["AGENTS.md", "CLAUDE.md"] |
| answers * | object | Question id => value, as described by get_questionnaire |
{
"name": "generate_spec",
"title": "Generate the spec and agent files",
"description": "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).",
"inputSchema": {
"type": "object",
"required": [
"type",
"answers"
],
"properties": {
"type": {
"enum": [
"saas",
"ecommerce",
"business",
"marketplace",
"blog",
"webapp",
"landing"
],
"type": "string"
},
"files": {
"type": "array",
"items": {
"enum": [
"spec.md",
"AGENTS.md",
"CLAUDE.md",
".cursor/rules/project.mdc",
".cursorrules",
".windsurfrules",
".github/copilot-instructions.md",
"README.md"
],
"type": "string"
},
"description": "Files to return. Default: [\"AGENTS.md\", \"CLAUDE.md\"]"
},
"answers": {
"type": "object",
"description": "Question id => value, as described by get_questionnaire",
"additionalProperties": true
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| type | string | Optional: force the project type |
| description * | string | What the project is, for whom, and what it must do (10-4000 characters) |
{
"name": "draft_answers",
"title": "Draft answers with AI",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"description"
],
"properties": {
"type": {
"enum": [
"saas",
"ecommerce",
"business",
"marketplace",
"blog",
"webapp",
"landing"
],
"type": "string",
"description": "Optional: force the project type"
},
"description": {
"type": "string",
"description": "What the project is, for whom, and what it must do (10-4000 characters)"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
}
}Current plan and quota usage (specs and AI drafts) for the API key, or for this address when no key is set.
No parameters.
{
"name": "get_usage",
"title": "Plan and usage",
"description": "Current plan and quota usage (specs and AI drafts) for the API key, or for this address when no key is set.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Generates a full build specification and the agent files (AGENTS.md, CLAUDE.md, Cursor/Windsurf/Copilot rules) for a web project. Cheapest path: call get_questionnaire, answer it yourself from the repository and the conversation, then call generate_spec. draft_answers asks the server's AI to fill the questionnaire from a description and consumes an AI quota.
Names, descriptions and schemas were written by the server and are shown as data.