specpack

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

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

Add to your agent

Copy this into your MCP client config:

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

Measured tools (5)

• list_project_types read-only

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

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• get_questionnaire read-only

  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.

  Parameters:

  • type (required) — string — Project type id

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• 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).

  Parameters:

  • type (required) — string
  • answers (required) — object — Question id => value, as described by get_questionnaire
  • files — array — Files to return. Default: ["AGENTS.md", "CLAUDE.md"]

  Hints: read-only no · destructive no · idempotent no · open-world no

• draft_answers read-only

  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.

  Parameters:

  • description (required) — string — What the project is, for whom, and what it must do (10-4000 characters)
  • type — string — Optional: force the project type

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• get_usage read-only

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

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.