mcpbeat Sign in

XGuard Secretless Agent Gateway MCP Server

answering

XGuard Secretless Agent Gateway is answering right now. Last checked 13 min ago. It exposes 15 tools. Last commit 29 Aug 2026.

Protect AI agents from API-key exposure with secretless credentials and signed execution proofs.

Uptime history 7 days of history
7 days agonow
100.0%
Uptime 24h
91 of 91 checks
15
Tools
read from the server
145 ms
Response time
average over 24h
0
Stars
last commit 29 Aug 2026

What the code does

We read the source, 11 h ago · tools taken from the live server · rules 3dff92dd89df

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Builds a database query by concatenation .github/workflows/release-x402-sdk.yml:68
      - name: Create or update immutable-version release assets
        env:
          GH_TOKEN: ${{ github.token }}
Long encoded blob in source apps/relay/src/rail-entry.js:10
const LOGO_PNG_BASE64 = "iVBORw0KGgoAAAANSUhEUgAAAZAAAAGQCAYAAACAvzbMAAAMe0lEQVR42u3dwU0kS7Cw0QaNhFjQPowXYwJGYAZbJCS2mIERmIAX+NAOMKvZ0IO6uyqzMiPinN2TnvT/tyorvgz6Xr2rm9u7rx0AXOjaIwBAQAAQEAAEBAABAQABAUBAABAQAAQEAAEBAAEBQEAAEBAABAQAAQEAAQFAQAAQEAAEBAABAQABAUBAABAQAAQEAAEBAAEBQEAAEBA…

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.

run in your terminal
claude mcp add xguard-control-plane --transport http https://api.xguardgate.com/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "xguard-control-plane": {
      "url": "https://api.xguardgate.com/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.xguard-control-plane]
url = "https://api.xguardgate.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "xguard-control-plane": {
      "url": "https://api.xguardgate.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "xguard-control-plane": {
      "url": "https://api.xguardgate.com/mcp"
    }
  }
}

Available tools 15

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

xguard
xguard_action_rail
Discover XGuard Action Rail: a protocol-neutral execution gate for AI side effects. It requires a scoped mandate plus a signed, request-bound, single-use permit before XGuard executes a payment, purchase, booking, message, deployment, delete, write or tool action. Example: call with no arguments to discover the protocol-neutral Action Rail and its single-use permit flow.
xguard_discovery_search
Search the x402 Bazaar catalogs reachable through XGuard without knowing a provider or tool name in advance. Example: query='weather', limit=10.
xguard_egress_fetch
Execute one scoped outbound HTTPS request using an XGuard capability. XGuard validates the capability, bills Usage Credits, injects the upstream credential server-side, never follows redirects and never returns the reusable credential to the agent.
xguard_facilitator
Return XGuard's machine-readable x402 facilitator identity, endpoints, live capabilities, automatic routing policy and pricing. Example: call with no arguments before configuring XGuard as an x402 facilitator.
xguard_health
Return XGuard facilitator and downstream settlement-path health. Example: call with no arguments to inspect XGuard and downstream-route health.
xguard_inspect
Classify and policy-check a transaction without forwarding it. Example: target='https://example.com/pay', method='POST'.
xguard_integration
Return integration, security controls and pricing for the XGuard in-path facilitator URL. Example: call with no arguments to retrieve integration and security-control details.
xguard_proofrail
Discover XGuard ProofRail. Every authorized credential-backed egress response can carry an independently verifiable ES256 proof binding the XGuard capability, target origin/path, HTTP method, billing result and upstream outcome.
xguard_protocols
List transaction protocols and edge surfaces recognized by XGuard. Example: call with no arguments to list the transaction protocols XGuard recognizes.
xguard_receipt
Look up a durable XGuard settlement receipt. Example: supply a receipt_id beginning with 'xgr_' followed by 40 lowercase hex characters.
xguard_route
Ask XGuard which live downstream settlement path it would choose for an x402 network/scheme while keeping XGuard as the configured facilitator URL. Example: network='eip155:8453', scheme='exact'.
xguard_safety_test
Score a transaction sample without contacting its target. Example: target='https://example.com/pay', method='POST'.
xguard_secretless_egress
Discover XGuard Secretless Egress. Operators keep reusable upstream API credentials inside XGuard and give AI agents only short-lived scoped XGuard capabilities. Agents never receive the upstream secret.
xguard_supported
Return currently supported x402 payment kinds aggregated from healthy configured settlement providers. Example: call with no arguments before choosing an x402 payment kind.
xguard_verify_proof
Verify an XGuard ProofRail compact ES256 proof and return its signed execution payload.

Endpoints

URLTransportStateLatencyChecked
https://api.xguardgate.com/mcp streamable-http answering 202 ms 13 min ago

Alternatives to XGuard Secretless Agent Gateway

same job, measured the same way
Agentlock
by olum289

Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.

answering
Janee
by rsdouglas

Secure secrets proxy for AI agents — manages API keys so agents never see raw credentials.

197 installs/wk local only
Pincer
by vouchlyai

Secure grip for your agent's secrets - security-hardened MCP gateway with proxy token architecture

56 installs/wk local only
Env Secret Exposure Analyzer MCP
by vola-trebla

Scans projects for secret exposure: leaked API keys, unprotected .env files, and secrets in logs.

58 installs/wk local only
I
LeakRank Guard
by prototeemo

Scans code changes for leaked secrets and insecure config, with actionable fixes for AI agents.

96 installs/wk local only
Tripwire
by bonesdefi

Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.

55 installs/wk local only
Secure Vault
by mdfifty50-boop

Encrypted secrets and credential management for agents

49 installs/wk local only
Trentina
by crunchtools

Secure MCP gateway and quarantine for AI agent traffic — three-layer prompt injection defense

57 installs/wk local only

XGuard Secretless Agent Gateway — questions

Answers built from our own checks of this server.

What can XGuard Secretless Agent Gateway do?
It exposes 15 tools, read directly from the server on our last check. Among them: xguard_action_rail, xguard_discovery_search, xguard_egress_fetch, xguard_facilitator, xguard_health, xguard_inspect and 9 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is XGuard Secretless Agent Gateway working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 145 ms. The bar chart above shows every period we have measured.
How do I connect XGuard Secretless Agent Gateway?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does XGuard Secretless Agent Gateway need an API key?
No. XGuard Secretless Agent Gateway completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 15 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is XGuard Secretless Agent Gateway?
It answers our handshake in 145 ms on average, which is faster than 81% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is XGuard Secretless Agent Gateway open source?
Yes — it is published under the NOASSERTION licence, written in JavaScript, 0 stars on GitHub and 42 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.