
MCPShelf Model Context Protocol Registry, Search & Security Auditor
io.github.RitualDev-LabPublished by GitHub account RitualDev-Labv1.0.0Updated Nov 19, 2026
Discover, audit trust scores, and 1-click install 400+ verified MCP servers for AI coding agents.
The publisher's own server: model.tools — Zero-Auth Agent Utilities
Overview
A local MCP registry browser that lets an assistant find, compare trust scores for, and get install snippets for 400+ MCP servers.
- What you can do
- Search and browse a synchronized catalog of 400+ MCP servers, with fuzzy search over the mirrored official registry
- Review independent security audit and trust scores covering supply-chain risk, permission checks and sandbox compatibility
- Retrieve copy-paste install configurations for Claude Desktop, Cursor, Windsurf and terminal/CLI use
- See community ratings and promoted or sponsored listings from the marketplace side
- When to use it
- Useful when you are choosing which MCP servers to add to a coding agent and want a searchable catalog with trust signals and ready-made configuration snippets instead of assembling them by hand.
- Requirements
- Runs as a local stdio process installed from the npm package; Node.js and npx are needed. No authentication, environment variables or headers are declared. Network access is implied for registry data and the hosted site.
Installation
In SourceWeft
- Open MCPShelf Model Context Protocol Registry, Search & Security Auditor in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
MCPShelf ⚡
The Open Model Context Protocol (MCP) Registry, Marketplace & Security Directory
[Live Marketplace] [Official Registry Mirror] [License: Apache-2.0] [GitHub Stars]
MCPShelf is an open-source, decentralized registry and web marketplace for Model Context Protocol (MCP) servers. Hosted live at mcp.ritualdev.in, it mirrors the official Model Context Protocol registry while providing instant fuzzy search, 1-click install snippets, verified security audit scores, community ratings, and a self-serve creator boosting platform.
🌟 Key Features
- ⚡ 419+ Synchronized MCP Servers: Fully synchronized with
registry.modelcontextprotocol.ionightly via automated GitHub Actions. - 🛡️ Security Audit Scores & Trust Engine: Independent trust ratings (0-10) assessing supply-chain vulnerabilities, permission checks, and sandbox compatibility.
- 🖱️ 1-Click Install Formats: Instant copy-paste JSON configurations for:
- Anthropic Claude Desktop (
claude_desktop_config.json) - Cursor IDE (
~/.cursor/mcp.json) - Windsurf (
~/.codeium/windsurf/mcp_config.json) - Terminal / CLI (
npx -y ...,uvx ...)
- Anthropic Claude Desktop (
- 🚀 Creator Self-Serve Boosting ("LinkedIn / X Promoted Spots"):
- Transparent promoted placements with
rel="sponsored"compliance. - Self-serve checkout powered by Dodo Payments & Stripe (via
@ritualdev-lab/mcp-monetize). - Tiers: Category Spotlight ($19/mo), Homepage Hero ($49/mo), and Enterprise Partner ($99/mo).
- Transparent promoted placements with
- 🤖 AEO / GEO & AI Search Native: Machine discovery manifests (
/llms.txt,/sitemap.xml,/robots.txt) optimized for AI search engines like Perplexity, ChatGPT, and Claude.
🚀 1-Click Quickstart Example
Install the AgentShield security firewall into Claude Desktop:
Or install DBShield database guardrail into Cursor:
💰 Self-Serve Creator Boosting Tiers
To promote your MCP server to thousands of AI developers building with Claude and Cursor:
Visit mcp.ritualdev.in/boost.html to activate instant boosting.
🛠️ Local Development & Contributing
Requirements
- Node.js >= 20.0.0
- npm / pnpm
Setup
📜 License & Governance
MCPShelf is open-source software licensed under the Apache-2.0 License. Maintained by RitualDev Lab.
Source: README.md at commit 6c65bd5
Tools
0Version history
1- v1.0.0LatestNov 19, 2026
Score
40% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.
Other Model integrations

model.tools — Zero-Auth Agent Utilities
tools.modelOfficial publisher
Zero-auth remote utility server giving agents disposable email OTP reading, durable checkpoints, webhook bins, wake timers, receipts and page-to-Markdown…
NLP.COM.AI Open Model Catalog
ai.com.nlpOfficial publisher
NLP.COM.AI Open Model Catalog's hosted MCP server, published by nlp.com.ai; no sign-in required; Streamable HTTP; 3 tools.

Hologram Model Hub
foundation.uor.hubOfficial publisher
A remote MCP server that lets an assistant search an index of open models and get verified download links with SHA-256 checksums.

DOC Model Safety Gate
Published by GitHub account laceykes
A local MCP server that stages AI-proposed content changes for human review and only lets reviewed runs publish.

ModelPick
Published by GitHub account Leizhidong-creator
Local stdio MCP server that recommends which AI model to use for each task node, with cost per solved task and connection setup.