XGuard — Agent Execution Gateway MCP server

online · 100% uptime

by moelayyan90·io.github.moelayyan90/xguard-control-plane·v5.2.0

No reviews yet

Scoped agent execution. Server-side credentials, policy, budgets and verifiable receipts.

B79/100grade B

Write a review Run it

What users say

No reviews yet

Be the first

Safety scan

B79/100

full report

Adoption

New

0 stars

Reviews

Write one

Nobody has reviewed XGuard — Agent Execution Gateway yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

XGuard — Agent Execution Gateway tools (8, 1 write)

write = sends, deletes, buys or posts

xguard_discoverFree
Find the paid API catalog and buying instructions, plus explicit provider operations and input schemas.
xguard_executewrite actionFree
Execute an explicit scoped provider operation, or a supported public-source outcome. intent:demo is free. Never infer a mutation from ambiguous text.
xguard_get_resultFree
Recover a paid public outcome with its payment identifier and original signed quote without execution or another payment.
xguard_preflightFree
Inspect validation, scope and remaining capability budget without reserving, billing or executing. Execution rechecks everything.
xguard_quoteFree
Inspect XGuard credit pricing for a capability, or obtain a signed x402 quote for a public outcome. Does not execute.
xguard_secretless_callFree
Call an allowed provider operation with a capability. Enforces scope, call/credit budget and billing before server-side credential injection. Writes require idempotency_key.
xguard_statusFree
Read observed execution/MCP metrics and configuration; empty observations do not imply uptime.
xguard_verify_receiptFree
Verify a ProofRail proof and optionally its bound x402 receipt and result digest. Signature validity does not prove source truth.

Public scan report

scanner v0.1.10 · 2026-10-02 · same rubric, same numbers if you re-run it

1 high

–Code scanremote-only server, no package to scann/a
Live reliabilityremote reachable in 653ms20/20
Tool poisoning8 tool descriptions checked15/15
Auth qualityopen endpoint exposes 1 write-action tools with no auth3/15
Maintenancelast push 9 days ago15/15
Maintainer identityregistry namespace matches repository owner6/10

Findings (1)

highWrite-action tools reachable without authenticationauth.open-write

Overall 79/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How XGuard — Agent Execution Gateway compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 79/100; higher than 58% of 4,460 AI and agents servers
Tools: 8; the typical AI and agents server has 6
Tools that change things: 13%; typical: 0%. Fewer write tools means less an agent can break
Uptime: 100%; of our recent checks; the typical remote AI and agents server answers 100%
Response time: 83 ms; faster than 90% of 2,331 AI and agents servers

What its tools let an agent do: 7 read · 1 change

Release history: 2 versions in the registry since 2026-09-10, latest 2026-09-20, typically one every 10 days.

Install XGuard — Agent Execution Gateway in Claude Code, Cursor or VS Code

claude mcp add --transport http xguard-control-plane https://api.xguardgate.com/mcp

Add to Cursor

What the publisher says

From the XGuard — Agent Execution Gateway repository's README, as published. We do not edit it. Read it on GitHub

XGuard — Paid API Gateway

Turn any API into a paid API for AI agents.

Register an existing HTTPS API, choose a request price and payout wallet, and share one paid URL. XGuard quotes, verifies and settles authorized payments, executes the request, returns a signed receipt and records platform fees and seller proceeds separately.

Monetize your API
Browse paid APIs
Gateway, fees, payout setup and buyer recovery
Small Workers, Express and FastAPI integrations
Revenue-path audit and acceptance limits

External seller routes stay draft without configured payout signing authority. A successful test is not a real customer payment. Production revenue acceptance requires a funded owner-authorized purchase and recorded settlement/delivery.

Scoped agent execution

Give agents capabilities, not reusable credentials.

Store a provider credential on the server, issue a scoped capability, and let an agent execute one authorized operation. XGuard enforces policy, expiration, revocation, budgets and idempotency before injecting the credential. Every completed execution returns a durable result and signed ProofRail evidence.

This branch contains the 5.2.0 release candidate. Its deployment is tracked in the release audit; the production version is reported by identity.

Operator setup: keep operator/provider keys out of agent context.
Agent contract: MCP, REST, JavaScript and Python examples.
Connect MCP: https://api.xguardgate.com/mcp.
Payment and recovery contract.

import { createExecutionClient } from './sdk/execution.js';
const agent = createExecutionClient({ capability: process.env.XGUARD_CAPABILITY });
const request = {
  operation: 'github.repository.read',
  input: { owner: 'moelayyan90', repo: 'XGuard' },
  idempotencyKey: 'read-xguard-repository-001'
};
await agent.preflight(request);
const output = await agent.execute(request);
// Retain the same key and exact input for recovery; never retry an uncertain write with a new key.
await agent.verify({ proof: output.proof, resultSha256: output.receipt.result_sha256 });

Sixteen explicit adapters cover bounded GitHub, Cloudflare, Slack, Notion, OpenAI, Anthropic, Gemini and Stripe operations. Provider permissions and fees remain operator-specific. Cloudflare deploys and Stripe money movement are not advertised. The free controlled Secretless demo proves authentication, scope denial, once-only execution and signature verification without an external provider or payment.

Public outcome examples

Public page extraction, product offers and feed digests remain secondary examples with their original prices and payment contracts.

Get your first result without an account, key, wallet or installation:

curl https://api.xguardgate.com/v1/execute \
  -H 'content-type: application/json' \
  -d '{"intent":"demo"}'

This runs the real extraction parser on labelled sample HTML. Supply html to process up to 12 KiB of your own document for free. The preview makes no external requests.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

XGuard — Agent Execution Gateway: common questions

Is XGuard — Agent Execution Gateway MCP server safe?: Mostly: it is graded B (79/100). Read the XGuard — Agent Execution Gateway safety report
How do I install XGuard — Agent Execution Gateway?: It runs remotely at api.xguardgate.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does XGuard — Agent Execution Gateway need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is XGuard — Agent Execution Gateway maintained?: The last commit was 42 days ago (2026-09-23). The latest release is v5.2.0.
Is XGuard — Agent Execution Gateway up?: 100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of XGuard — Agent Execution Gateway?: Servers from other publishers that do the same job: DCC-MCP Core MCP server, Ausca MCP server and agent-device MCP server.
How does XGuard — Agent Execution Gateway compare with other AI and agents MCP servers?: safety score 79/100 (higher than 58% of 4,460 AI and agents servers); tools 8 (the typical AI and agents server has 6); tools that change things 13% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to XGuard — Agent Execution Gateway

Same job from other publishers: the closest match first, then the best rated.

DCC-MCP Core
Agent control plane for DCC and engine hosts: one MCP endpoint, one tool contract.
not reviewed
Established
A
Ausca
Pay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.
not reviewed
Established
A
agent-device
Let AI agents inspect, control, and debug real iOS, Android, desktop, and TV apps
not reviewed
Widely used
A
agent-device
Open source device layer for AI agents: control mobile, web, TV, and desktop apps over MCP
not reviewed
Widely used
A
Decionis
Authorize consequential AI agent actions before execution
not reviewed
Established
A

Run it through the gateway

With the gateway added, ask your agent for it by name:

agent prompt

call io.github.moelayyan90/xguard-control-plane → xguard_discover

Free per call. Metered, capped by your key, logged for reliability.

Add the gateway (gw.mcp.market)

Rating: —
Safety grade: B · 79/100
Stars: 0
Downloads/wk: –
Price: Free
Licence: NOASSERTION
Transport: Remote
Uptime: 100% · 28/28 checks
Version: 5.2.0
Category: AI and agents
Last release: 2026-09-23

Endpoint

https://api.xguardgate.com/mcp

streamable-http

Own this server?

Claim it to keep the listing current and reply to reviews. Claiming never changes the grade or hides a review.

Claim listing

Badge for your README

Shows the safety grade and links back to this page. It updates itself after every scan and review.

[![mcp.market](https://mcp.market/badge/moelayyan90-xguard-control-plane.svg)](https://mcp.market/server/moelayyan90-xguard-control-plane)

How the badge works