Governed MCP Gateway
Provides integration with Stripe for settling agent spend proposals via Stripe meter events, acting as a payment rail for the spend mandate plane.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Governed MCP GatewayList tools available to my current authenticated identity."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@cubiczan/governed-mcp-gateway
HTTP MCP control plane (default port 7474). Principal on every tools/call and every SSE frame — not a tool catalog.
Production MCP auth often dies when work hops threads or workers. This gateway resolves a Bearer credential to a Principal, injects it into params._meta.cubiczan.principal, repeats it on SSE, enforces allowlists, rotates vaulted secrets in place, and runs a lightweight CHP spend gate before priced tools.
Install / run
npm i -g @cubiczan/governed-mcp-gateway # or use npx
npx -y @cubiczan/governed-mcp-gateway
# → http://127.0.0.1:7474From source:
npm install
npm run build
npm start
npm testRelated MCP server: governed-mcp-gateway
Cursor / Claude config
Start the gateway in a terminal (or a process manager), then point the client at the HTTP MCP endpoints:
{
"mcpServers": {
"governed-gateway": {
"url": "http://127.0.0.1:7474/mcp",
"headers": {
"Authorization": "Bearer mcp_agt_payops_demo"
}
},
"chp": {
"command": "npx",
"args": ["-y", "@cubiczan/chp-mcp"]
},
"conductor": {
"command": "npx",
"args": ["-y", "@cubiczan/agent-conductor"]
}
}
}Demo keys: mcp_agt_payops_demo, mcp_agt_research_demo, mcp_human_controller_demo.
Stack
┌─────────────────┐ ┌──────────────────────────┐ ┌────────────────────┐
│ Cursor / Claude │────▶│ governed-mcp-gateway │────▶│ spend-mandate-plane│
│ (MCP client) │ SSE │ :7474 principal+vault │ opt │ :7475 │
└────────┬────────┘ └────────────┬─────────────┘ └────────────────────┘
│ │
│ stdio │ CHP gate (embedded)
▼ ▼
┌─────────────────┐ ┌──────────────────────────┐
│ @cubiczan/ │ │ @cubiczan/chp-mcp │
│ agent-conductor │ │ Profile B spend / HITL │
└─────────────────┘ └──────────────────────────┘Sister packages: @cubiczan/chp-mcp, @cubiczan/agent-conductor, consensus-hardening-protocol.
API
Method | Path | Auth | What |
|
| — |
|
|
| Bearer | JSON-RPC |
|
| Bearer | SSE with principal on |
|
| Human | Put a named secret |
|
| Human | New hash, same name |
|
| — |
|
|
| Human | CHP approve / reject |
curl -sS -H "Authorization: Bearer mcp_agt_payops_demo" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"echo.ping","arguments":{"hello":"world"}}}' \
http://127.0.0.1:7474/mcpNotes
This is an HTTP MCP gateway (JSON-RPC + SSE), not a stdio MCP process. The
governed-mcp-gatewaybin starts the HTTP server.Shared CHP / HTTP / ledger helpers are vendored under
src/shared/(no@cubiczan/sharedworkspace dep).Optional: set
SPEND_PLANE_URLto hook the spend-mandate plane before priced tools.
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Related MCP Connectors
Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.
- FullmaktOAuthai.fullmakt
Credential broker for AI agents: scoped, revocable API access with policy enforcement and audit.
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
Runtime permission, approval, and audit layer for AI agent tool execution.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables controlled AI-agent access to enterprise-shaped tools with a deny-by-default gated write path, human approval, dry-run execution, and append-only audit logging.1-
- AlicenseNot gradedqualityCmaintenanceThis MCP server preserves a Bearer principal on every tool call and SSE frame, rotates vaulted credentials in place, and enforces per-tool allowlists for agents.MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to safely call MCP tools through a security gateway that enforces per-role authorization and least-privilege tool scoping.-
- AlicenseNot gradedqualityCmaintenanceEnables secure support-ticket and customer-account operations with signed JWT authentication, prompt-injection and tool-poisoning guardrails, and human-in-the-loop confirmation for destructive actions.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/icohangar-ops/governed-mcp-gateway'
If you have feedback or need assistance with the MCP directory API, please join our Discord server