What does “pre‑execution enforcement” mean?
Forbidden actions are blocked before the agent runs them, rather than being logged afterward.
@arian-gogani
基本信息
Pre-execution enforcement and tamper-evident audit trails for AI agents. Hash-chained action logs, Ed25519 signatures, covenant policy language. EU AI Act Article 12 ready. Works with Claude Desktop, Cursor, VS Code.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"nobulex": {
"command": "npx",
"args": [
"@nobulex/mcp-server"
]
}
}
}Set covenant rules using permit/forbid/require syntax. Each rule is a string like 'forbid delete_user' or 'permit read_data safe to read'.
Check whether an action is allowed or blocked by the current covenant rules.
Returns the full hash-chained audit trail of all compliance checks.
Independently verify the integrity of the hash-chained audit log. Detects any tampering.
A compliance server for AI agents that enforces behavior policies before execution, creates tamper-evident audit trails using hash-chaining (SHA-256 + Ed25519), and uses the covenant policy language to define allowed actions. It targets compliance with the EU AI Act Article 12 and enables independent third-party audits.
Install via npm install @nobulex/mcp-server and configure it with a supported client such as Claude Desktop, Cursor, or VS Code. Declare agent policies using the covenant policy language to specify which actions are permitted or forbidden.
Forbidden actions are blocked before the agent runs them, rather than being logged afterward.
They use hash chaining with SHA‑256 and Ed25519 signatures, and any third party can verify the chain independently.
The server works with Claude Desktop, Cursor, and VS Code.

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
评论