Kakunin
Brings enterprise-grade identity and compliance tooling to AI agents through X.509 certificate management, risk scoring, and comprehensive audit logging. If you're building agents that need to operate under MiCA or the EU AI Act, this handles the credential infrastructure and paper trail regulators expect. The focus is squarely on the compliance layer: verifiable agent identities, decision tracking, and risk assessment hooks. You'd reach for this when your AI deployment needs to answer "which agent did what and when" in a legally defensible way, or when you need cryptographic proof of agent identity rather than API keys.
- GitHub stars
- 1
- tools
- 3
- auth
- Secret needed
- transport
- STDIO
- env vars
- 2
- last updated
- Jul 8, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
verify_agent_scopeCheck whether this agent is authorised to perform an action before executing it. Verifies the active X.509 certificate, permitted_actions scope, financial limits, and revocation status.
Check whether this agent is authorised to perform an action before executing it. Verifies the active X.509 certificate, permitted_actions scope, financial limits, and revocation status.
No parameter schema in public metadata yet.
check_risk_scoreRetrieve the agent's rolling 30-day risk score, band (low/medium/high), drift trend, and actionable guidance. No input required.
Retrieve the agent's rolling 30-day risk score, band (low/medium/high), drift trend, and actionable guidance. No input required.
No parameter schema in public metadata yet.
audit_log_appendAppend a behavioral event to the agent's immutable audit log. Returns risk score + transaction ID. Events scoring ≥ 0.85 auto-trigger a certificate revocation check.
Append a behavioral event to the agent's immutable audit log. Returns risk score + transaction ID. Events scoring ≥ 0.85 auto-trigger a certificate revocation check.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
KAKUNIN_API_KEYsecretKakunin API key (kak_live_... or kak_test_...). Obtain at https://kakunin.ai/dashboard.
KAKUNIN_AGENT_IDID of the agent this MCP server acts on behalf of (agt_...).
Readme
@kakunin/mcp — MCP server for AI agent identity & compliance
Model Context Protocol server for the Kakunin AI agent compliance API. Lets AI agents self-verify scope, check their own risk score, and log behavioral events — all from within Claude, Cursor, or any MCP-compatible runtime.
npx @kakunin/mcp
Tools
verify_agent_scope
Check whether this agent is authorised to perform an action before executing it. Verifies the active X.509 certificate, permitted_actions scope, financial limits, and revocation status.
Details
- Repository
- github.com/nqzai/kakunin-mcp
- Package
@kakunin/mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active