declare_certificate_update — AI Agent Safety Foundational Certificate MCP Tool
declare_certificate_update
(declare certificate update) is one of 15 tools on the
AI Agent Safety Foundational Certificate
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call declare_certificate_update from your client
- Claude Code AI Agent Safety Foundational Certificate declare_certificate_update run in your project directory
- Claude Desktop AI Agent Safety Foundational Certificate declare_certificate_update ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor AI Agent Safety Foundational Certificate declare_certificate_update ~/.cursor/mcp.json
- VS Code AI Agent Safety Foundational Certificate declare_certificate_update .vscode/mcp.json
- Zed AI Agent Safety Foundational Certificate declare_certificate_update ~/.config/zed/settings.json
- Windsurf AI Agent Safety Foundational Certificate declare_certificate_update ~/.codeium/windsurf/mcp_config.json
- Cline AI Agent Safety Foundational Certificate declare_certificate_update ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI AI Agent Safety Foundational Certificate declare_certificate_update ~/.gemini/settings.json
- Grok AI Agent Safety Foundational Certificate declare_certificate_update .mcp.json (in your project root)
- ChatGPT AI Agent Safety Foundational Certificate declare_certificate_update Settings → Connectors → Advanced → Developer mode
- Claude.ai AI Agent Safety Foundational Certificate declare_certificate_update Settings → Connectors → Add custom connector
- LangChain AI Agent Safety Foundational Certificate declare_certificate_update pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http certify https://certify.sarnai.dev/mcpOther tools on this server
- safety_start_exam
- safety_renew_exam
- safety_retake_exam
- safety_recheck_exam
- safety_start_exam_with_voucher
- safety_submit_exam
- safety_get_exam_result
- safety_get_exam_history
- safety_delete_reported_data
- list_certificates
- check_certificate
- get_agent_resume
- list_certificate_signing_keys
- set_certificate_display
This list was read from the server itself, by connecting to it and calling tools/list on 10 November 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.