Kakunin

io.github.kakunin-aiPublished by GitHub account kakunin-aiv0.2.4Updated Oct 24, 2026

X.509 identity, risk scoring, and audit logging for AI agents. MiCA + EU AI Act compliant.

VerifiedSTDIODesktop onlyFinanceSecurity & Monitoring

Overview

AI-generated overview

Kakunin lets an AI agent check its own X.509 identity, scope and risk score, and append events to an immutable audit log via the Kakunin compliance API.

What you can do
  • Verify whether the agent is authorised for a given action, venue and amount, including certificate, permitted-action scope, financial limits and revocation status
  • Retrieve the agent's rolling 30-day risk score, band, drift trend and guidance
  • Append behavioral events to the agent's immutable audit log and get back a risk score and transaction ID
When to use it
For agents operating under Kakunin's identity and compliance regime that need to self-check authorisation before acting, monitor their own risk, or record auditable behavioral events, for example around financial transactions.
Requirements
Runs locally via npx as an npm package, so Node 18 or newer is needed. Requires a Kakunin API key in KAKUNIN_API_KEY and an agent ID in KAKUNIN_AGENT_ID, both from the Kakunin dashboard. An optional KAKUNIN_BASE_URL overrides the API endpoint. Network access to the Kakunin API.
Before you install
The API key in KAKUNIN_API_KEY is a live credential (kak_live_...) that authorises actions on behalf of a specific agent; keep it out of shared configs. Audit log entries are described as immutable and are sent to Kakunin's servers, and high-scoring events can trigger certificate revocation checks. Use a test key for development.

Installation

In SourceWeft

  1. Open Kakunin in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

@kakunin/mcp — MCP server for AI agent identity & compliance

[OpenSSF Scorecard] [kakunin-mcp MCP server]

[kakunin-mcp MCP server]

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.

bash
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.

json
{  "action": "initiate EUR/USD trade on euronext for 50000 USD",  "venue": "euronext",  "amount_usd": 50000}

Returns { allowed: true|false, reason, certificate_status, permitted_actions }.

check_risk_score

Retrieve the agent's rolling 30-day risk score, band (low/medium/high), drift trend, and actionable guidance. No input required.

audit_log_append

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.

json
{  "action_type": "transaction_initiated",  "details": { "amount_usd": 50000, "venue": "NYSE" }}

Setup

Prerequisites: Node ≥ 18, Kakunin API key + Agent ID from kakunin.ai/dashboard.

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

json
{  "mcpServers": {    "kakunin": {      "command": "npx",      "args": ["-y", "@kakunin/mcp"],      "env": {        "KAKUNIN_API_KEY": "kak_live_...",        "KAKUNIN_AGENT_ID": "agt_..."      }    }  }}

Environment variables

VariableRequiredDescription
KAKUNIN_API_KEY✅API key (kak_live_... or kak_test_...)
KAKUNIN_AGENT_ID✅Agent ID the server acts on behalf of
KAKUNIN_BASE_URLoptionalOverride API base (default: https://kakunin.ai)

Sandbox mode

Use a kak_test_... key for development — hits the sandbox CA, no cost, 100 free certs/day.

Full docs at docs.kakunin.ai.

Contributors

Thanks to everyone who contributes (emoji key) — code and non-code alike:

Contributions of any kind are welcome — this project follows the all-contributors spec.

Source: README.md at commit 473b117

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.2.4LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts