mcpField
M

mcp-gateway

Local
github.com/authzxSecurity0Updated 11w ago

About mcp-gateway

mcp-gateway is an authorization proxy between AI agents and downstream MCP servers, for teams that need policy checks before tool calls run. It supports cloud or local policy evaluation and records structured audit logs.

Key features

  1. 01Checks each tool call before forwarding
  2. 02Supports cloud and local authorization
  3. 03Defines local policies with .rego files
  4. 04Records structured audit logs
  5. 05Serves over stdio or HTTP

Use cases

  1. 01Limit agent access to database tools
  2. 02Block unauthorized file or SQL operations
  3. 03Share a governed gateway among remote agents
  4. 04Trace tool callers, arguments, and decisions

MCP support

The MCP server proxies requests between clients and downstream MCP servers, checking authorization before forwarding tool calls. It exposes policy-enforced tools over stdio or Streamable HTTP.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"authzx-mcp-gateway": {
"command": "npx",
"args": [
"-y",
"@authzx/mcp-gateway"
],
"env": {
"YOUR_API_KEY": "<YOUR_API_KEY>"
}
}
}
}
Run commandnpx -y @authzx/mcp-gateway
Environment variables to set
YOUR_API_KEYSecretYour API key for the service

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@authzx/mcp-gateway1.0.1

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Vengtoo MCP Gateway

License Node npm

Authorization gateway for AI agents and MCP tool calls.

Open-source. Drop-in. Works with any MCP client.

Why

AI agents connected to MCP servers can call any tool they have access to: read your database, delete files, execute arbitrary SQL. Vengtoo MCP Gateway puts a policy enforcement point between the agent and those tools, so every call is authorized before it executes.

What it does

  • Sits between MCP clients (Claude Code, Cursor, VS Code, GitHub Copilot) and any MCP server
  • Intercepts every tool call and checks authorization before forwarding
  • Two modes: cloud (Vengtoo Cloud API) and local (Vengtoo Agent + .rego policy file)
  • Full audit trail of every tool invocation: subject, tool name, arguments, and decision are logged as structured JSON:
{"ts":"2026-05-25T10:03:11.482Z","level":"info","msg":"mcp_tool_call","subject":"agent:ai-assistant","tool":"database__query","allowed":true,"latency_ms":0.8}

Quick Start

  1. Install and start the Vengtoo Agent. The agent runs locally and evaluates your authorization policy; no cloud account needed.
go install github.com/vengtoo/agent/cmd/agent@latest
vengtoo-agent --policy ./policy.rego

Create a policy.rego to define what your agent can do:

package vengtoo.mcp

default allow := false

# Allow read-only tools
allow if { input.resource.name == "database__query" }
allow if { input.resource.name == "database__list_tables" }

# Allow writes, but block destructive SQL
allow if {
    input.resource.name == "database__execute"
    not contains(lower(input.resource.attributes.sql), "drop")
    not contains(lower(input.resource.attributes.sql), "delete from")
}

See demo/policies/ for more examples including Kubernetes namespace protection.

  1. Create a gateway.config.json:
{
  "vengtoo": {
    "agentUrl": "http://127.0.0.1:8181"
  },
  "subject": "agent:ai-assistant",
  "servers": {
    "database": {
      "command": "node",
      "args": ["./my-database-mcp-server.js"]
    }
  }
}
  1. Add to your MCP client (e.g. Claude Code):
claude mcp add --transport stdio vengtoo-gateway -- \
  npx vengtoo-mcp-gateway --config /path/to/gateway.config.json

Configuration

Config schema
FieldTypeRequiredDescription
vengtoo.agentUrlstring*URL of local Vengtoo Agent (local mode)
vengtoo.cloudUrlstring*URL of Vengtoo Cloud API (cloud mode)
vengtoo.apiKeystringAPI key from Vengtoo Cloud (or set VENGTOO_API_KEY env var)
vengtoo.timeoutMsnumberAuthorization request timeout (default: 5000)
subjectstringyesIdentity of the agent making tool calls
subjectTypestringSubject type (default: "agent")
resourceTypestringResource type for authorization checks (default: "mcp_tool")
serversobjectyesMap of downstream MCP servers to proxy
transportstringCaller transport: "stdio" (default) or "http", see Transport
httpobjectHTTP transport settings (used when transport is "http")

* Provide either agentUrl (local mode) or cloudUrl (cloud mode).

Each entry in servers has:

FieldTypeRequiredDescription
commandstringyesCommand to spawn the MCP server
argsstring[]Command arguments
envobjectAdditional environment variables

Modes

Cloud mode

Connect to Vengtoo Cloud for managed policies:

{
  "vengtoo": {
    "cloudUrl": "https://api.vengtoo.com/access/v1/evaluation",
    "apiKey": "vgt_..."
  },
  "subject": "agent:prod-assistant",
  "servers": {
    "database": {
      "command": "node",
      "args": ["./db-server.js"]
    }
  }
}
Local mode

Run the Vengtoo Agent locally with a .rego policy file for offline, self-contained authorization:

# Start the agent with your policy
vengtoo-agent --policy ./policy.rego
{
  "vengtoo": {
    "agentUrl": "http://127.0.0.1:8181"
  },
  "subject": "agent:dev-assistant",
  "servers": {
    "database": {
      "command": "node",
      "args": ["./db-server.js"]
    }
  }
}

Transport

The gateway exposes its (policy-enforced) tools to callers over one of two transports.

stdio (default)

Runs as a local subprocess speaking MCP over stdin/stdout: the right choice for a single desktop agent (Claude Desktop, Cursor, Claude Code). No network surface.

HTTP (remote)

Runs a Streamable HTTP MCP server at a URL, so a remote agent (or many concurrent agents) can share one governed gateway. Enable it with --http (or "transport": "http" in the config):

vengtoo-mcp-gateway --config gateway.config.json --http --port 8808
{
  "vengtoo": { "cloudUrl": "https://api.vengtoo.com/access/v1/evaluation", "apiKey": "vgt_..." },
  "subject": "agent:prod-assistant",
  "transport": "http",
  "http": {
    "port": 8808,
    "host": "0.0.0.0",
    "path": "/mcp",
    "authTokens": ["<caller-token>"],
    "allowedHosts": ["gateway.example.com"]
  },
  "servers": { "database": { "command": "node", "args": ["./db-server.js"] } }
}

HTTP config (http.*):

FieldTypeDefaultDescription
portnumber8808TCP port to listen on
hoststring127.0.0.1Interface to bind; 0.0.0.0 accepts remote connections
pathstring/mcpURL path of the MCP endpoint
callersobject[]-Per-caller identity: { "token": "...", "subject": "agent:claude" }; each bearer token authorizes as its own subject
authTokensstring[]-Anonymous bearer tokens; grant access, run as the global subject
allowedHostsstring[]-Enables DNS-rebinding protection; rejects requests with an unlisted Host
allowedOriginsstring[]-Enables DNS-rebinding protection; rejects requests with an unlisted Origin

Per-caller identity. Give each agent its own token and subject, and your policies (and audit trail) see each caller's real identity through one shared gateway:

"http": {
  "port": 8808,
  "callers": [
    { "token": "<claude-token>", "subject": "agent:claude" },
    { "token": "<cursor-token>", "subject": "agent:cursor" }
  ]
}

Also settable via VENGTOO_GATEWAY_HTTP_CALLERS="<token>=agent:claude,<token>=agent:cursor". Sessions are bound to the token that opened them: a different caller presenting another caller's session id gets a 401, so identities cannot cross sessions. Tokens listed in authTokens (or callers omitted entirely) run as the config's global subject.

Safety: the gateway refuses to bind a non-loopback interface with no caller auth (callers or authTokens). Either configure tokens, or set VENGTOO_GATEWAY_ALLOW_UNAUTHENTICATED=true to knowingly expose an open endpoint. An unauthenticated GET /healthz liveness probe is always served.

⚠️ Security: Vengtoo trusts whichever subject this gateway asserts. The callers token→subject mapping above (owned by this gateway's own config) is the correct pattern; it is NOT the same as trusting a client-supplied header. Never change this to derive the subject from a header/field a calling client sends; that would let any caller claim to be any subject and inherit its permissions within your tenant. If you front this gateway with another reverse proxy, make sure that proxy cannot be made to forward an arbitrary caller-chosen bearer token or subject.

CLI Flags

FlagDescription
--config <path>Path to gateway config file (default: ./gateway.config.json)
--httpServe over HTTP instead of stdio
--port <n>HTTP listen port (default: 8808; implies --http-compatible config)
--host <h>HTTP bind interface (default: 127.0.0.1)
--path <p>HTTP endpoint path (default: /mcp)
--list-toolsList all tools from configured downstream servers and exit
--generate-policy [path]Generate a starter .rego policy file for the configured tools (default: policy.rego)

Environment overrides: VENGTOO_API_KEY, VENGTOO_AGENT_URL, VENGTOO_SUBJECT, VENGTOO_GATEWAY_TRANSPORT (http), VENGTOO_GATEWAY_PORT / PORT, VENGTOO_GATEWAY_HOST, VENGTOO_GATEWAY_PATH, VENGTOO_GATEWAY_HTTP_TOKENS (comma-separated), VENGTOO_GATEWAY_ALLOW_UNAUTHENTICATED.

MCP Client Setup

The gateway runs as a stdio MCP server. Point your MCP client at it instead of the downstream server directly.

Claude Code
claude mcp add --transport stdio vengtoo-gateway -- \
  npx vengtoo-mcp-gateway --config /path/to/gateway.config.json
Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "vengtoo-gateway": {
      "command": "npx",
      "args": ["vengtoo-mcp-gateway", "--config", "/path/to/gateway.config.json"]
    }
  }
}
Claude Desktop

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

{
  "mcpServers": {
    "vengtoo-gateway": {
      "command": "npx",
      "args": ["vengtoo-mcp-gateway", "--config", "/path/to/gateway.config.json"]
    }
  }
}
VS Code / GitHub Copilot

Add to .vscode/mcp.json:

{
  "servers": {
    "vengtoo-gateway": {
      "type": "stdio",
      "command": "npx",
      "args": ["vengtoo-mcp-gateway", "--config", "/path/to/gateway.config.json"]
    }
  }
}

See demo/ for full end-to-end examples with sample policies.

Roadmap

See ROADMAP.md for what's planned: per-caller OAuth, downstream resilience, dynamic tool lists, metrics, remote downstream servers, and more.

Feedback

License

Apache-2.0, see LICENSE.

Comments

Markdown supported

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.