ActionFence

AI Action Firewall for MCP servers and APIs.

One line of code. Signed receipts. Simulation mode.

Why ActionFence?

AI agents can now book flights, send emails, and delete records in your system — often without you knowing until the invoice arrives. ActionFence lets you define exactly what they're allowed to do, and proves every decision with a signed receipt.

It sits in front of your MCP tools or HTTP routes and decides whether an incoming agent action is allowed before your real handler runs.

It gives you:

• Policy enforcement from guard-policy.json
• Identity tiers: anonymous, token, verified
• Built-in verified JWT support via JWKS
• Capability scope checks from JWT capabilities
• Per-action spend caps plus session/day spend limits
• Request and transaction rate limiting
• Signed, hash-chained receipts in SQLite
• Simulation mode for dry-run previews

Install

npm install actionfence

Quick Start

MCP Server

import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
import { withGuard } from 'actionfence';

const server = new McpServer({ name: 'my-server', version: '1.0.0' });

withGuard(server, {
  policy: './guard-policy.json',
  identityReaderOptions: {
    jwksUri: 'https://issuer.example/.well-known/jwks.json',
    issuer: 'https://issuer.example',
    audience: 'bookflight-mcp',
  },
});

server.registerTool('search_flights', {}, async () => {
  return { content: [{ type: 'text', text: 'results...' }] };
});

Express / Fastify

import express from 'express';
import { guard } from 'actionfence';

const app = express();
app.use(express.json());

app.use(
  guard({
    policy: './guard-policy.json',
    identityReaderOptions: {
      jwksUri: 'https://issuer.example/.well-known/jwks.json',
      issuer: 'https://issuer.example',
      audience: 'bookflight-api',
    },
    actionResolver: (toolName) => {
      if (/^GET \/bookings\/[^/]+$/.test(toolName)) {
        return 'GET /bookings/:id';
      }
      return toolName;
    },
    spendExtractor: (params) => {
      const body = (params as { body?: { amount?: number } })?.body;
      return body?.amount ?? null;
    },
  }),
);

CLI

npx actionfence init
npx actionfence validate guard-policy.json
npx actionfence simulate guard-policy.json --action book_flight --identity verified --spend 250

Using an AI Coding Assistant?

Copy this prompt into Claude, Cursor, Copilot, or any LLM and let it handle the setup:

Install and integrate the "actionfence" npm package into my current project. Read the full integration guide at https://raw.githubusercontent.com/saifeldeen911/actionfence/main/llms-full.txt then: install the package, create a guard-policy.json for my use case, and wire up the middleware.

Policy File

guard-policy.json defines what agents can do in your system.

{
  "$schema": "https://raw.githubusercontent.com/saifeldeen911/actionfence/main/schemas/guard-policy.schema.json",
  "service": "BookFlight.com",
  "version": "1.0",
  "default_rule": "deny",
  "actions": {
    "search_flights": {
      "allowed": true,
      "identity": "any"
    },
    "book_flight": {
      "allowed": true,
      "identity": "verified",
      "max_spend": 500,
      "currency": "USD",
      "requires_human_approval": true
    },
    "bulk_booking": {
      "allowed": false
    }
  },
  "rate_limits": {
    "requests_per_minute": 30,
    "transactions_per_day": 5
  },
  "spend_limits": {
    "session_max": 1000,
    "daily_max": 2500,
    "currency": "USD"
  },
  "regulations": ["EU_AI_Act_Art50"]
}

Policy Reference

Action Rule Fields

Identity Tiers

Verified identity is built in when you configure identityReaderOptions.jwksUri and JWKS lookup succeeds from cache or the remote endpoint. If JWKS retrieval or network access fails, ActionFence may fall back to token identity; invalid signatures, wrong issuers or audiences, unknown kids, and other cryptographic verification failures stay anonymous or rejected.

Scope Enforcement

If a decoded or verified token includes a capabilities claim, ActionFence treats it as an exact allowlist of policy action names. A request that passes policy checks but is not listed in capabilities is blocked.

Simulation Mode

Simulation mode runs the full policy pipeline without executing the handler or storing a receipt.

MCP

withGuard(server, {
  policy: './guard-policy.json',
  simulate: true,
});

Express

app.use(
  guard({
    policy: './guard-policy.json',
    simulate: true,
  }),
);

CLI output

actionfence simulate guard-policy.json --action book_flight --identity verified --spend 250

SIMULATION - actionfence

  Action:          book_flight
  Tool:            book_flight
  Identity:        verified
  Status:          PASS
  Spend:           250.00
  Session total:   250.00
  Daily total:     250.00
  Human approval:  required
  Rate limit:      29/30 remaining

Action Receipts

Every enforced decision stores a signed receipt in SQLite.

receipt_id:     a1b2c3d4-...
timestamp:      2026-05-07T14:02:11Z
agent_id:       agt_7x9f2k...
action:         book_flight
status:         PASSED
payload_hash:   0x8f3a...
prev_hash:      0x7e2d...
receipt_sig:    0x4f9b...

Receipts are:

• Hash-chained
• HMAC-SHA256 signed
• Append-only
• Verifiable with ReceiptStore.verifyChain()

Note: Receipts are stored in a local SQLite file (.actionfence/receipts.db). This works perfectly for single-instance deployments. If you run multiple server instances, each will maintain its own receipt chain. PostgreSQL backend for multi-instance deployments is planned for v0.2.

Signing key resolution order:

1. options.secret
2. ACTIONFENCE_SECRET
3. .actionfence/key

API Reference

withGuard(server, options)

const guardInstance = withGuard(server, {
  policy: './guard-policy.json',
  simulate: false,
  silent: false,
  secret: process.env.ACTIONFENCE_SECRET,
  identityReaderOptions: {
    jwksUri: 'https://issuer.example/.well-known/jwks.json',
    issuer: 'https://issuer.example',
    audience: 'bookflight-mcp',
  },
  actionResolver: (toolName, params) => toolName,
  spendExtractor: (params) => null,
  onDecision: (decision) => {},
  watchPolicy: true,
});

guardInstance.dispose();

guard(options)

const middleware = guard({
  policy: './guard-policy.json',
  identityReaderOptions: {
    jwksUri: 'https://issuer.example/.well-known/jwks.json',
  },
});

GuardOptions

IdentityReaderOptions

0.1.0 Limits

• Capability checks are exact string matches only
• No APoP / LAS-WG adapters yet
• No wildcard scope patterns or path-policy DSL
• requires_human_approval flags the receipt and fires onDecision — no built-in approval workflow yet (use the callback to build your own)
• SQLite receipt store is single-instance only — PostgreSQL backend coming in v0.2
• Money is major-unit only; mixed-currency accounting is out of scope for one policy

CLI Reference

actionfence init

actionfence init
actionfence init --service MyAPI
actionfence init --output ./policies/guard-policy.json

actionfence validate <path>

actionfence validate guard-policy.json

actionfence simulate <path>

actionfence simulate guard-policy.json --action search_flights
actionfence simulate guard-policy.json --action book_flight --identity verified --spend 250

Examples

• MCP Server Example
• Express API Example

Development

git clone https://github.com/saifeldeen911/actionfence.git
cd actionfence
npm install
npm run typecheck
npm run lint
npm test
npm run build

License

MIT (c) Saifeldeen