Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Nobulex MCP Compliance Server Set a rule to forbid all admin actions."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Prior direction, kept rather than deleted. This repository is from the covenant and receipts era of the name. Current work is a decision-integrity gateway for automated financial actions: nobulex.com. Nothing below is retracted. It is simply not what is being built now.
This banner previously described the reliability registry as the current direction and called it independent. The registry is itself now a prior direction, and nothing here has been independently verified by anyone.
Nobulex MCP compliance server — covenant rule checking, hash-chained audit logs, and integrity verification for any MCP-compatible agent.
Tool | Description |
| Set covenant rules using |
| Check if an action is allowed or blocked by current rules |
| Return the full hash-chained audit trail |
| Verify integrity of the audit chain (detect tampering) |
Related MCP server: gov-mcp
forbid delete_user Users cannot be deleted
permit read_data Safe to read
require approval Must get approval first
forbid admin.* All admin actions blocked
forbid * Lockdown modeRules are evaluated in order — first match wins. Unmatched actions are allowed by default.
Add to your claude_desktop_config.json:
{
"mcpServers": {
"nobulex": {
"command": "npx",
"args": ["-y", "@nobulex/mcp-server"]
}
}
}Config file locations:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Add to your Cursor MCP settings:
{
"mcpServers": {
"nobulex": {
"command": "npx",
"args": ["-y", "@nobulex/mcp-server"]
}
}
}The server uses stdio transport. Run it with:
npx @nobulex/mcp-servernpm install
npm run build
npm testMIT
Check whether an action is allowed or blocked by the current covenant rules.
Inputs: action (required), params.
Returns the full hash-chained audit trail of all compliance checks.
Inputs: no named parameters.
Set covenant rules using permit/forbid/require syntax. Each rule is a string like 'forbid delete_user' or 'permit read_data safe to read'.
Inputs: rules (required).
Independently verify the integrity of the hash-chained audit log. Detects any tampering.
Inputs: no named parameters.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 4 tools
Each tool has a clearly distinct purpose: check_action evaluates rules, get_audit_log retrieves logs, set_rules configures rules, and verify_log validates log integrity. There is no overlap in functionality, making tool selection straightforward for an agent.
All tool names follow a consistent verb_noun pattern (check_action, get_audit_log, set_rules, verify_log) with clear, descriptive verbs. There are no deviations in naming style, ensuring predictability across the toolset.
With 4 tools, the server is well-scoped for compliance management, covering rule checking, configuration, log retrieval, and integrity verification. Each tool earns its place without redundancy or bloat, fitting typical MCP server ranges.
The toolset provides strong coverage for core compliance workflows: rule management, enforcement, and audit logging. A minor gap exists in lacking tools for rule listing or deletion, but agents can work around this using existing tools like set_rules and get_audit_log.
Governed MCP: agent audit, provenance, deterministic checks, and receipt-backed FragGate execution.
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
Live behavioral security verifier, schema auditor, and trust oracle for A2A, MCP & x402 agents.
Hash-chained HMAC-signed audit log MCP for A2A (agent-to-agent) calls. Every tool-call, agent-ha...