Manufact MCP Catalog: Quality Scoring and Leaderboard for Model Context Protocol Servers

LinkManufactTool

Manufact has launched an MCP directory and automated quality evaluation tool. It audits Model Context Protocol endpoints against compatibility guidelines for marketplaces like the ChatGPT Apps Store and Claude Cloud Connectors.

Key points

  1. Directory of over 1,000 curated MCP servers ranked by an automated quality score across multiple categories.
  2. Score weighted across tool documentation (40%), tool definitions (30%), protocol compatibility (20%), and server metadata (10%).
  3. Supports MCP Apps evaluation (20% share when present) without penalising servers lacking UI widgets.
  4. Checks adherence to marketplace requirements such as JSON Schemas, Claude's 64-character tool name limit, and behaviour annotations.
  5. Generates ready-to-copy fix prompts for coding agents without executing live tools during the scan.

Why it matters

As MCP becomes the standard for AI tool integrations in ChatGPT and Claude, pre-submission audits help developers catch formatting, schema, and protocol mistakes before submitting their tools to public app directories.

Analysis

Manufact leverages this catalog and validator to anchor its platform within the MCP developer workflow. By focusing on static metadata, Streamable HTTP handshakes, and UI widget envelopes without invoking tools, the service acts as a low-friction pre-flight check that reduces marketplace review failures.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 16 October 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • X post:pederzh

    Manufact Launches Global MCP Leaderboard and Quality Score

    Manufact has launched a public catalog and global leaderboard for Model Context Protocol (MCP) servers. Developers can submit their HTTPS endpoints to receive an automated quality score out of 100 along with compliance feedback tailored for platforms like the ChatGPT Apps Store and Claude Cloud Connectors.

    290bookmarks29.5kviews

    AI & LLMs· Announcement

  • Repository:anthropics/claude-plugins-official

    Anthropic's Official Claude Code Plugins Directory

    Anthropic manages claude-plugins-official, a curated directory and marketplace for Claude Code plugins. The repository houses both official tools and reviewed third-party extensions that package skills, slash commands, and MCP servers.

    36.1kstarsPython

    AI & LLMs· Resource

  • Repository:affaan-m/agentshield

    AgentShield: Security Auditor for Claude Code and MCP Configurations

    AgentShield is an open-source TypeScript security scanner designed for AI agent setups. It inspects `.claude/` directories to detect hardcoded secrets, unverified MCP servers, hook injection vulnerabilities, and tool permission misconfigurations.

    1.2kstarsTypeScript

    AI & LLMs· Tool

  • Repository:modelcontextprotocol/modelcontextprotocol

    Model Context Protocol (MCP): Official Specification and Documentation

    The modelcontextprotocol/modelcontextprotocol GitHub repository provides the formal specification, protocol schema, and official documentation for the Model Context Protocol (MCP).

    9.1kstarsTypeScript

    AI & LLMs· Resource

  • Article:Anthropic

    Anthropic Brings MCP 2026-07-28 to Claude

    Anthropic announced the rollout of the fifth Model Context Protocol specification release, MCP 2026-07-28, across Claude products. The update introduces a stateless request/response core, standardises extensions like MCP Apps and Tasks, and hardens enterprise authorisation via OAuth 2.0 and OIDC.

    AI & LLMs· Announcement

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.