Manufact Launches Global MCP Leaderboard and Quality Score

X postpederzhAnnouncement

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.

Key points

  1. Manufact ranks over 1,050 curated MCP servers across categories such as Developer Tools, Data & Analytics, Productivity, and Finance.
  2. The Quality Score is calculated based on tool documentation (40%), tool definitions (30%), protocol compatibility (20%), and server metadata (10%), with MCP Apps accounting for 20% when present.
  3. Audits are conducted by inspecting the streamable HTTPS endpoint, evaluating JSON Schemas, annotations, and handshake compatibility without executing the tools.
  4. The catalog doubles as a pre-submission checklist for marketplaces like the ChatGPT Apps Store and Claude Cloud Connectors, checking criteria such as Claude's 64-character limit for tool names.
  5. Testing is free and does not require a Manufact account to generate public reports and listings.

Why it matters

As the MCP ecosystem rapidly expands, standardisation and documentation rigor become critical for reliable AI agent integration. A transparent scoring system helps developers discover well-maintained servers and fix metadata flaws prior to marketplace review.

Analysis

By offering automated auditing and a public ranking, Manufact positions its platform at the center of MCP tooling infrastructure. While the scoring focuses on static metadata, naming conventions, and protocol compliance rather than runtime reliability, these factors directly determine whether LLMs can reliably parse and invoke external tools.

Original post

pederzh

@pederzh · 14 October 2026

BREAKING: the global MCP leaderboard is live on t.co/bytElgAneo t.co/NVTqBBfQg7 t.co/MVwKTQD78C

203 likes14 replies290 bookmarks29.5k views

View on X
More posts in the thread (8)
  1. @jancurn @apify coming! would love to set up cross-harness tests for your mcp on @manufact !
  2. @jjacky submit it here: t.co/bytElgAneo
  3. @ngemberling @kevnsn I want to see @tray in the leaderboard!
  4. @jalcowastaken @andrelandgraf where's @mastra?
  5. @ngemberling @kevnsn @tray submit it!
  6. @nikhilrado benchmax it!
  7. @apatheticmagpie @ClickHouseDB goated
  8. @danvernon @pietrozullo we should add an "HR & hiring" category
Selected replies (5)
  • @jancurn @pederzh @apify 94/100 should be enough to rank high, no? t.co/GNyqT3mv95
  • @danvernon @pederzh how do i get on your frontpage? :D t.co/lUGZmNcDQg
  • @jancurn @pederzh Oh no, where is @apify? 🙈
  • @the_versecafe @pederzh t.co/L5rkmQgu5B
  • @jjacky @pederzh how can we get OR mcp on here?

Mentioned links

Links and tools from this entry

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.

  • Repository:xdevplatform/xmcp

    xmcp: FastMCP Server for the X API

    xmcp is a Python-based Model Context Protocol (MCP) server that exposes the X API OpenAPI specification as callable tools using FastMCP, allowing AI agents to interact with X endpoints.

    853starsPython

    AI & LLMs· Tool

  • 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

  • X post:ClaudeDevs

    Model Context Protocol 2026-07-28: Stateless Core and Hardened Enterprise Auth Released

    Anthropic has released the fifth Model Context Protocol specification update (MCP 2026-07-28). The major architectural change shifts MCP to a stateless request/response core, simplifying deployment on serverless and edge infrastructure. The release also formalises an extensions framework and aligns authentication with enterprise OAuth 2.0 and OIDC standards.

    7.9kbookmarks2.8mviews

    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.