Register
Model Context Protocol Server Register
This register inventories Model Context Protocol (MCP) servers the organization operates internally, consumes from third parties, or permits AI assistants to invoke. MCP is the canonical pattern for exposing tools, data sources, and capabilities to AI agents; each MCP server is a security boundary that must be governed, monitored, and reviewed.
- Type
- Register
- Version
- 1.0.14
- Date
- 2026-10-27
- Owner
- AI Security Maintainer
- Approving authority
- Governance Library Maintainer
- Classification
- Public
- Confidentiality
- Public
- Category
- AI Governance
- Review frequency
- Quarterly and continuously updated upon server registration, change, or retirement
- Licence
- CC BY-SA 4.0
Read the full text on GitHub (opens in a new tab)
Outline
- Purpose
- Scope
- Register schema
- Approval categories
- Server-security baseline
- Operating expectations
- Coordination with adjacent governance
- Operating metrics
- Framework alignment
- Limitations
Frameworks it maps to
- MCP specification
- ISO/IEC 42001:2023
- OWASP LLM Top 10
- MITRE ATLAS
- NIST AI RMF 1.0
- NIST SP 800-53 Rev. 5
- ISO/IEC 27001:2022
Related documents
- AI Access and Agent Permissions Standardai
- AI and Agentic Development Security Standardai
- AI Security and Risk Standardai
- Model Registryai
- AI System Register Templateai
- guardrails/
ai/ sourcemcp-security.md (opens in a new tab) - Supplier Security and Privacy Assurance Standardsupply-chain
Next
All Documents