mcp-registry

Vinkius Connector Registry — Open Data Initiative

Welcome to the Vinkius Open Data Initiative. We are opening access to the Vinkius connector catalog. This repository provides automatically updated documentation for 10,672 unique connectors for AI agents.

Research & Training Applications

This highly structured corpus is designed specifically for AI researchers, data scientists, and language model developers. It provides a robust foundation for advancing artificial intelligence research in the following domains:

• LLM Fine-Tuning: Real-world schemas for training models in advanced function calling and tool utilization.
• Agentic Frameworks: Operational metadata for studying multi-agent orchestration and system bridging.
• Semantic Analysis: A large-scale dataset for analyzing how external software platforms and enterprise systems are mapped to natural language interfaces.

Data Provenance

Extracted programmatically from the Vinkius registry, each record maintains strict structural integrity. The dataset is rigorously indexed with categorical taxonomies, precise tool support configurations, and environmental metadata to ensure a noise-free corpus.

Dataset at a Glance

Schema Reference

Research & Use Cases

This dataset enables a range of applications across AI research, product development, and market intelligence:

Ecosystem Intelligence

• Map the growth trajectory of MCP server categories over time.
• Identify which tool types (database, API, file system, communication) are expanding fastest.

Prompt Engineering

• Analyze prompt_examples to study how tool-use instructions are designed for different LLM integrations.
• Build prompt template corpora for fine-tuning or evaluation benchmarks.

Quality & Reliability Analysis

• Explore the distribution of debugger_grade and debugger_score to identify patterns in high-quality vs. poorly maintained servers.
• Correlate tools_count with reliability scores to measure complexity vs. stability trade-offs.

Machine Learning

• Multi-label classification — Predict category or tags from description using NLP models.
• Recommendation systems — Build tool recommenders based on tag similarity, embedding distance, or collaborative filtering.
• Anomaly detection — Flag servers with abnormal score patterns or sudden grade changes across snapshots.

Market & Competitive Research

• Track the rate of new server registrations as a proxy for MCP ecosystem adoption.
• Benchmark server categories against industry verticals for strategic planning.

Update Frequency

This dataset is automatically synchronized every 12 hours from the Vinkius platform. Each snapshot reflects the most current listings, tool inventories, debugger scores, and quality grades available.

Citation

If you use this dataset in your research or product, we appreciate a citation:

@dataset{vinkius_mcp_registry,
  title   = {Vinkius Connector Registry — Global AI Agent Connector Dataset},
  author  = {Vinkius},
  year    = {2026},
  url     = {https://huggingface.co/datasets/Vinkius/mcp-registry},
  note    = {Updated every 12 hours. 10,672+ connectors indexed.}
}

About Vinkius

Vinkius is the connectivity layer and connector catalog for AI agents. With 10,672+ connectors cataloged, graded, and deployable in one click, Vinkius is the definitive catalog for discovering and connecting AI agents — Claude, Cursor, GPT, Copilot, and any MCP-compatible client — to the tools they need.

Beyond the catalog, Vinkius delivers a full infrastructure stack: MCP Governance (DLP, policies, compliance and audit), Sandboxes (isolated V8 execution for AI agents), Analytics (observability, cost and performance), and an MCP Inspector that runs 34 automated checks to grade every server from A+ to F.

The platform is backed by open source projects including MCP Fusion (the MCP server framework for TypeScript), MCP Desktop, Discover MCP, and Doc-Breach.

Trusted by engineers from Google, NVIDIA, Amazon, JPMorgan Chase, Red Hat, and more — Vinkius is where the MCP ecosystem is cataloged, tested, and connected.

Independent Platform Disclaimer

Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by any third-party company listed in this dataset. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use in this dataset is strictly for informational purposes to identify service compatibility and interoperability.

License

This dataset is released under the CC0 1.0 Universal (Public Domain) license. You are free to use, modify, and distribute it for any purpose — commercial or non-commercial — without attribution requirements, though citation is appreciated.