About kakunin
@kakunin/mcp is an MCP server for AI agent identity and compliance, used with the Kakunin API. It lets agents verify authorization, inspect risk scores, and append behavioral events to an audit log.
Key features
- 01Verify action scope and authorization
- 02Check rolling risk scores and trends
- 03Append events to an immutable audit log
- 04Check certificates and financial limits
Use cases
- 01Validate an agent action before execution
- 02Review an agent's risk status
- 03Record an agent behavior event
- 04Check permitted actions and transaction limits
MCP support
Exposes Kakunin API tools for agent scope verification, risk scoring, and audit logging to MCP-compatible runtimes. It requires a Kakunin API key and Agent ID.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @kakunin/mcpKAKUNIN_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_...).Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
3Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| venue | string | No | Optional trading venue or system being accessed (e.g. "euronext", "xetra"). |
| action | string | Yes | The action or endpoint the agent wants to perform. Can be a scope string (e.g. "write:invoices"), an API path (e.g. "/api/v1/execute_trade"), or a plain description (e.g. "initiate EUR/USD trade on euronext for 50000 USD"). |
| amount_usd | number | No | Optional transaction amount in USD for financial scope enforcement. |
Details
From the project 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.
{
"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.
{
"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:
{
"mcpServers": {
"kakunin": {
"command": "npx",
"args": ["-y", "@kakunin/mcp"],
"env": {
"KAKUNIN_API_KEY": "kak_live_...",
"KAKUNIN_AGENT_ID": "agt_..."
}
}
}
}
Environment variables
| Variable | Required | Description |
|---|---|---|
KAKUNIN_API_KEY | ✅ | API key (kak_live_... or kak_test_...) |
KAKUNIN_AGENT_ID | ✅ | Agent ID the server acts on behalf of |
KAKUNIN_BASE_URL | optional | Override 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.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.