ZBS Index What actually exists in applied AI, with the source next to it

mcp server

io.github.cdeust/prd-spec-generator

Turns a feature description into a verified 9-file PRD — multi-judge consensus, 17 MCP tools.

Description as published by the maintainer. Source

  • version 0.6.1
  • active

active — Most recent push to the repository was 2026-08-04.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
GitHub stars 2 Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. cumulative, all time GitHub
Last commit 2026-08-04 Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. point in time GitHub
Open issues 5 Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. as of fetch GitHub
Latest published version 0.6.1 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-08-03 When the registry record was last updated by its maintainer. point in time Model Context Protocol
License MIT Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. as of fetch GitHub
First listed in the MCP Registry 2026-08-02 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
repository status active The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. as of fetch GitHub

Where to get it

Related, by what their authors tagged them

  • io.github.cdeust/ai-architect-mcp-spec — last commit 2026-08-04, shares ai-architect, claude-code-plugin, gemini-cli
    PRD verification and host-driven generation with multi-judge consensus across 17 MCP tools.
  • E2LLM — last commit 2026-07-31, shares specification
    E2LLM gives your AI eyes and hands in a real browser: structured perception (SiFR) plus action.
  • Hashloom — last commit 2026-07-26, shares spec-driven-development, verification
    Content-addressed contracts and a verification cache that cut agent context by skipping proven code.
  • Heddle — last commit 2026-07-26, shares spec-driven-development, verification
    Content-addressed contracts and a verification cache that cut agent context by skipping proven code.
  • com.babyblueviper/invinoveritas — last commit 2026-08-05, shares verification
    AI-agent verifier: verdict committed before the outcome graded against it; /review, /ledger.
  • dev.safeprompt/mcp — last commit 2026-08-03, shares validation
    Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.
  • io.github.agenson-horrowitz/agent-output-guard — last commit 2026-04-05, shares validation
    Validate and verify data from other agents before acting on it. Zero LLM costs.
  • DOS — the trust substrate for agent fleets — last commit 2026-07-17, shares verification
    Verify what agents actually shipped, arbitrate file collisions, refuse with structured reasons.
  • io.github.archradhq/deterministic — last commit 2026-05-21, shares validation
    Deterministic IR/IR-LINT validation, policy packs, drift vs exports (archrad). Apache-2.0.
  • AgentTrust — last commit 2026-04-27, shares verification
    Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.

These share tags the maintainers applied themselves, such as ai-architect, claude-code-plugin, gemini-cli, multi-judge. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

Also from cdeust

How the author describes it

Topics the maintainer set on GitHub: ai-agents, ai-architect, claude-code, claude-code-plugin, codex, gemini-cli, llm-tools, mcp, mcp-server, model-context-protocol, multi-judge, prd, product-requirements, requirements-engineering, spec-driven-development, specification, stateless-reducer, typescript, validation, verification.

Bring your own setup

We take apart real AI setups every week and show what broke, what cost too much, and what the trace actually said. If you run agents on real work, that is where the useful conversation is.

Join ZBS AI Practice Lab

Sources

  1. cdeust/prd-spec-generator on GitHub — GitHub, observed , trust tier 3.
  2. Official MCP Registry — Model Context Protocol, observed , trust tier 1.