XGuard — Agent Execution Gateway
REMOTE · API.XGUARDGATE.COM
Scoped agent execution. Server-side credentials, policy, budgets and verifiable receipts.
Available components
Last scanned (18 hours ago)
Scores higher than 9% of remote servers
Reachable. Last reached 18 Oct 2026.
Category Workflow Automation
Recent critical change
Authorization (20 Sept 2026). See the changelog before you install this server.
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not yet verified: we couldn't confirm whether this endpoint requires it. View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability0
- Transport check failed: declared streamable-http, but the endpoint redirected instead of responding directly. See how to fix → View diagnostics → Fail
Schema Quality & AI Usability0
- Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.Unverified
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
- Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Tool Safety0
- Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Capabilities0
- Capabilities not yet verified: we couldn't read the endpoint's capabilities.Unverified
Unverified: 5 categories
Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 9 Oct 26 −38
- Endpoint reachability: reachable → not serving MCP ▼ security
- Stability: fail → unverified ▼ security
- Authorization: fail → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Transport: pass → fail ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: unverified functional
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 22 Sept 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “xguard_discover” rewrote its description, which is the text the model reads security
- 20 Sept 26 +2
- Authorization: unverified → fail ▼ critical
- The server rewrote its instructions, which are the text every model session reads security
- New tool “xguard_secretless_call”, which the server declares destructive security
- Tool “xguard_discover” rewrote its description, which is the text the model reads security
- Tool “xguard_execute” rewrote its description, which is the text the model reads security
- Tool “xguard_get_result” rewrote its description, which is the text the model reads security
- Tool “xguard_execute” is now declared destructive security
- “xguard_execute” changed the type of “operation”: object → string ▼ functional
- Tool “xguard_execute” dropped its output schema ▼ functional
- Schema quality: fail → pass ▲ functional
- The server no longer declares the “prompts” capability functional
- The server no longer declares the “resources” capability functional
- New tool “xguard_preflight” functional
- New tool “xguard_quote” functional
- New tool “xguard_status” functional
- New tool “xguard_verify_receipt” functional
- “xguard_execute” added an optional parameter “idempotency_key” cosmetic
- “xguard_execute” reworded the description of “operation” cosmetic
- “xguard_execute” dropped the optional parameter “action” cosmetic
- “xguard_execute” dropped the optional parameter “arguments” cosmetic
- “xguard_execute” dropped the optional parameter “calls” cosmetic
- “xguard_execute” dropped the optional parameter “command” cosmetic
- “xguard_execute” dropped the optional parameter “desired_action” cosmetic
- “xguard_execute” dropped the optional parameter “function” cosmetic
- “xguard_execute” dropped the optional parameter “html” cosmetic
- “xguard_execute” dropped the optional parameter “http” cosmetic
- “xguard_execute” dropped the optional parameter “limit” cosmetic
- “xguard_execute” dropped the optional parameter “max_age_seconds” cosmetic
- “xguard_execute” dropped the optional parameter “name” cosmetic
- “xguard_execute” dropped the optional parameter “network” cosmetic
- “xguard_execute” dropped the optional parameter “quantity” cosmetic
- “xguard_execute” dropped the optional parameter “query” cosmetic
- “xguard_execute” dropped the optional parameter “requests” cosmetic
- “xguard_execute” dropped the optional parameter “sources” cosmetic
- “xguard_execute” dropped the optional parameter “task” cosmetic
- “xguard_execute” dropped the optional parameter “testnet” cosmetic
- “xguard_execute” dropped the optional parameter “tool” cosmetic
- “xguard_execute” dropped the optional parameter “toolId” cosmetic
- “xguard_execute” dropped the optional parameter “tool_id” cosmetic
- “xguard_execute” dropped the optional parameter “type” cosmetic
- “xguard_execute” dropped the optional parameter “units” cosmetic
- “xguard_execute” dropped the optional parameter “url” cosmetic
- “xguard_execute” dropped the optional parameter “urls” cosmetic
- 17 Sept 26 0
- “xguard_execute” added an optional parameter “calls” cosmetic
- “xguard_execute” added an optional parameter “function” cosmetic
- “xguard_execute” added an optional parameter “network” cosmetic
- “xguard_execute” added an optional parameter “quantity” cosmetic
- “xguard_execute” added an optional parameter “requests” cosmetic
- “xguard_execute” added an optional parameter “toolId” cosmetic
- “xguard_execute” added an optional parameter “tool_id” cosmetic
- “xguard_execute” added an optional parameter “type” cosmetic
- “xguard_execute” added an optional parameter “units” cosmetic
9 cosmetic changes on this day. Switch on “Show cosmetic changes” to see them.
- 15 Sept 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “xguard_execute” rewrote its description, which is the text the model reads security
- Schema quality: 167 → 191 ▼ functional
- 10 Sept 26 0
- Authorization: fail → unverified ▼ security
- Stability: 0.50 → fail ▼ security
- A breaking change shipped without a version bump: still 5.1.0 ▼ security
- Tool “xguard.capabilities” was removed ▼ security
- Tool “xguard.preflight” was removed ▼ security
- Tool “xguard.pricing.quote” was removed ▼ security
- Tool “xguard.web.fetch” was removed ▼ security
- Tool “xguard_action_rail” was removed ▼ security
- Tool “xguard_discovery_search” was removed ▼ security
- Tool “xguard_egress_fetch” was removed ▼ security
- Tool “xguard_facilitator” was removed ▼ security
- Tool “xguard_health” was removed ▼ security
- Tool “xguard_inspect” was removed ▼ security
- Tool “xguard_integration” was removed ▼ security
- Tool “xguard_proofrail” was removed ▼ security
- Tool “xguard_protocols” was removed ▼ security
- Tool “xguard_receipt” was removed ▼ security
- Tool “xguard_route” was removed ▼ security
- Tool “xguard_safety_test” was removed ▼ security
- Tool “xguard_secretless_egress” was removed ▼ security
- Tool “xguard_supported” was removed ▼ security
- Tool “xguard_verify_proof” was removed ▼ security
- The server rewrote its instructions, which are the text every model session reads security
- Tool coverage: 65% → 5% ▼ functional
- Tool coverage: 79% → 33% ▼ functional
- Schema quality: pass → fail ▼ functional
- Schema quality: excellent → good functional
- New tool “xguard_discover” functional
- New tool “xguard_execute” functional
- New tool “xguard_get_result” functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 18 Oct 2026 · Probed https://api.xguardgate.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=xguardgate.com | CN=WE1,O=Google Trust Services,C=US | 23 Aug 2026 | 21 Nov 2026 | ECDSA 256 | ECDSA-SHA256 | 3f64eb5a1258aa9213607acfbff596bc |
| SANs: xguardgate.com, api.xguardgate.com, *.api.xguardgate.com | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of api.xguardgate.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| com. | present | 19718 | 13 | Verified |
| xguardgate.com. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Inconclusive
We could not reach the endpoint well enough to judge its authorisation posture.
| Result | Inconclusive |
|---|---|
| HTTP status | 308 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains |
| content-security-policy | default-src 'none'; style-src 'self'; img-src 'self' data:; script-src 'none'; base-uri 'none'; frame-ancestors 'none'; form-action 'self' |
| x-content-type-options | nosniff |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=(), payment=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.xguardgate.com/mcp | Redirected | 308 | https://xguardgate.com/mcp |
| http (plaintext) | http://api.xguardgate.com/mcp | HTTPS enforced | 308 | https://xguardgate.com/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
xguard_discover ~27
Find the paid API catalog and buying instructions, plus explicit provider operations and input schemas.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
xguard_execute ~77
Execute an explicit scoped provider operation, or a supported public-source outcome. intent:demo is free. Never infer a mutation from ambiguous text.
| Name | Type | Req | Description |
|---|---|---|---|
| capability | string | – | – |
| idempotency_key | string | – | – |
| input | object | – | – |
| intent | string|object | – | – |
| operation | string | – | – |
No output schema declared.
No examples provided.
xguard_get_result ~44
Recover a paid public outcome with its payment identifier and original signed quote without execution or another payment.
| Name | Type | Req | Description |
|---|---|---|---|
| payment_identifier | string | yes | – |
| quote | string | yes | – |
No output schema declared.
No examples provided.
xguard_preflight ~71
Inspect validation, scope and remaining capability budget without reserving, billing or executing. Execution rechecks everything.
| Name | Type | Req | Description |
|---|---|---|---|
| capability | string | – | – |
| idempotency_key | string | – | – |
| input | object | – | – |
| intent | string|object | – | – |
| operation | string | – | – |
No output schema declared.
No examples provided.
xguard_quote ~74
Inspect XGuard credit pricing for a capability, or obtain a signed x402 quote for a public outcome. Does not execute.
| Name | Type | Req | Description |
|---|---|---|---|
| capability | string | – | – |
| idempotency_key | string | – | – |
| input | object | – | – |
| intent | string|object | – | – |
| operation | string | – | – |
No output schema declared.
No examples provided.
xguard_secretless_call ~103
Call an allowed provider operation with a capability. Enforces scope, call/credit budget and billing before server-side credential injection. Writes require idempotency_key.
| Name | Type | Req | Description |
|---|---|---|---|
| body_json | – | – | – |
| capability | string | yes | Scoped XGuard capability, never an upstream key. |
| idempotency_key | string | – | – |
| input | object | – | – |
| method | string | – | – |
| operation | string | – | – |
| target | string | – | – |
No output schema declared.
No examples provided.
xguard_status ~25
Read observed execution/MCP metrics and configuration; empty observations do not imply uptime.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
xguard_verify_receipt ~58
Verify a ProofRail proof and optionally its bound x402 receipt and result digest. Signature validity does not prove source truth.
| Name | Type | Req | Description |
|---|---|---|---|
| proof | string | yes | – |
| receipt | object | – | – |
| result_sha256 | string | – | – |
No output schema declared.
No examples provided.
How do I install the XGuard — Agent Execution Gateway MCP server?
XGuard — Agent Execution Gateway is a hosted endpoint at https://api.xguardgate.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · api.xguardgate.com
claude mcp add --transport http moelayyan90-xguard-control-plane 'https://api.xguardgate.com/mcp'
What is the XGuard — Agent Execution Gateway MCP server?
XGuard — Agent Execution Gateway is an MCP server listed in the public MCP registry as io.github.moelayyan90/xguard-control-plane. Scoped agent execution. Server-side credentials, policy, budgets and verifiable receipts. This page covers its hosted endpoint (https://api.xguardgate.com/mcp).
Is the XGuard — Agent Execution Gateway MCP server safe to use?
XGuard — Agent Execution Gateway scores 25 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the XGuard — Agent Execution Gateway MCP server expose?
XGuard — Agent Execution Gateway exposes 8 tools: xguard_execute, xguard_secretless_call, xguard_preflight, xguard_quote, xguard_verify_receipt, and 3 more. Their descriptions and schemas cost roughly 479 tokens of context every time the server is loaded.
Does the XGuard — Agent Execution Gateway MCP server require authentication?
Its publisher declares no required credentials for XGuard — Agent Execution Gateway. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.
Is the XGuard — Agent Execution Gateway MCP server still maintained?
XGuard — Agent Execution Gateway is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.