ServGhost MCP server
com.servghost/servghostservghost.comstreamable-httpv1.0.0Scanned
Rent offshore VPS, dedicated, RDP and GPU servers in 7 jurisdictions; crypto-only, no KYC
11 tools: 3 do something that can't be undone, 2 change things and 6 only read.
- Reads private data · 1
- Reads text others write · 1
- Can send data out · 1
- No findings
Sign-in required, no OAuth metadata. Remote posture
Anlyon alternative
5 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the ServGhost MCP server can do
The ServGhost MCP server is published by servghost.com, a domain the MCP Registry verified. It has 11 tools. It can do things that cannot be undone, such as sending, paying or publishing (topup_create, topup_bonus and server_action) and create or change data (2 tools: quote and create_order), but cannot delete data. 6 tools only read.
1 tool reads private data (server_credentials); 1 tool brings in text other people can write (server_credentials); 1 tool can send data out of your system (server_action). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Last scanned Nov 1, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
11 tools
Can't be undone 3Claude Code: ask
server_actionSend a lifecycle command to a server: reboot, shutdown, start, reinstall, or console_link.Can send data outNo findings
Why it is in this group
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe description's first verb is "send": it sends or publishes something to other people.
Description, as the server wrote it Send a lifecycle command to a server: reboot, shutdown, start, reinstall, or console_link.
topup_bonusReturn the bonus credit tiers applied to top-ups.No findings
Why it is in this group
- The name "topup_bonus" says "topup": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it Return the bonus credit tiers applied to top-ups. Use this BEFORE topup_create so you can pick an amount that maximises free credit. No auth required.
topup_createTop up your USD balance with crypto.No findings
Why it is in this group
- The name "topup_create" says "topup": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it Top up your USD balance with crypto. Minimum $30, maximum $2000 per top-up. Bonus credit is applied automatically on confirmation: $100 → +$25, $250 → +$75, $500 → +$200, $1000 → +$500, $1500 → +$1000, $2000 → +$2000 (linear interpolation between anchors, no bonus below $100). Call topup_bonus first to see the full tier table. Returns a payment_id, deposit address and amount_crypto — send it from your wallet, then poll payment_status(order_id=payment_id) until status=confirmed.
Changes things 2Claude Code: ask
create_orderDeploy a server from your USD balance.No findings
Why it is in this group
- The name "create_order" says "create": a word for a change.
Description, as the server wrote it Deploy a server from your USD balance. BALANCE-ONLY: you must topup_create first (min $30, see topup_bonus for free credit tiers), wait for the topup to confirm, then call this. If your balance is short, returns {insufficient_balance: true, topup_required: true, deficit_usd, topup: {suggested_usd, suggested_bonus, ...}} — call topup_create with that amount and retry. If no account_token is provided, a new account is created and the token is returned — STORE IT. Server is active immediately on success.
quoteCalculate the final price (USD) for a plan + location + billing period, including discounts and any RAM / disk / extra-IP upgrades.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Calculate the final price (USD) for a plan + location + billing period, including discounts and any RAM / disk / extra-IP upgrades.
Only reads 6Show 6 read-only tools
account_balanceReturn the current USD balance for an account.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return the current USD balance for an account. Use this to decide whether you can call create_order or need to topup_create first.
agent_helpReturn the canonical 4-call recipe for buying a server, with examples.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return the canonical 4-call recipe for buying a server, with examples. Call this first if you are unsure how to use the tools.
list_locationsList the 7 offshore jurisdictions AnonPort operates in, with privacy/legal features.No findings
Why it is in this group
- The name "list_locations" says "list": a word for reading.
Description, as the server wrote it List the 7 offshore jurisdictions AnonPort operates in, with privacy/legal features.
list_plansList all VPS, dedicated, RDP or GPU plans with prices per location.No findings
Why it is in this group
- The name "list_plans" says "list": a word for reading.
Description, as the server wrote it List all VPS, dedicated, RDP or GPU plans with prices per location. RDP is only available in NL/RO/MD/RU. GPU is only available in IS/NL/RO/MD (Russia excluded due to NVIDIA export controls).
payment_statusPoll the status of a top-up (or legacy crypto-direct order).No findings
Why it is in this group
- The name "payment_status" says "status": a word for reading.
Description, as the server wrote it Poll the status of a top-up (or legacy crypto-direct order). pending → confirmed (balance credited + bonus applied) for topups; pending → confirmed → active for legacy orders. After a topup confirms, call create_order to deploy.
server_credentialsFetch IP, root password and console URL for a server, once status is active.Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "fetch": a word for reading.
What it can reach
- private-dataThe name "server_credentials" says "credential": it reads secrets.
- private-dataThe description's first sentence says "fetch" and "password": it reads secrets.
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Fetch IP, root password and console URL for a server, once status is active.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
1 path in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__servghost__server_action"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:46 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 404
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
The probe stopped: initialize answered HTTP 404.
Posture changes
- Nov 6, 2026
- HTTP status of an anonymous initialize: 200 to 404
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 5 to 0
- Protocol version: 2025-03-26 to none
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 404; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 5 -> 0 (and 1 more).View diff
- HTTP status of an anonymous initialize: 200 to 404
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 5 to 0
- Protocol version: 2025-03-26 to none
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http servghost https://servghost.com/mcpclaude mcp add --transport http servghost https://servghost.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__servghost__list_plans",
"mcp__servghost__list_locations",
"mcp__servghost__account_balance",
"mcp__servghost__payment_status",
"mcp__servghost__server_credentials",
"mcp__servghost__agent_help"
],
"ask": [
"mcp__servghost__quote",
"mcp__servghost__create_order",
"mcp__servghost__topup_create",
"mcp__servghost__topup_bonus",
"mcp__servghost__server_action"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as servghost. Review it before you use it.
Capability tags behind 2 rules
- mcp__servghost__server_credentials private-data, untrusted-input
- mcp__servghost__server_action outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.servghost/servghost/verify?hash=9b2cfbdb87920db4b38ae78ba91aa9b5c55c3aa84c2f8e50c19ca194d62653fb" | jq -e '.changed == false'Pinned hash 9b2cfbdb8792, from Nov 1, 2026, 08:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.servghost/servghost/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.servghost/servghost)Source: MCP Registry. Synced Oct 21, 2026, 18:04 UTC.
ServGhost MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ServGhost MCP server safe?
- No scan can promise that. What its definitions show: 11 tools, 5 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the ServGhost MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the ServGhost MCP server do things that cannot be undone?
- Yes. 3 tools can send, pay, publish or merge: topup_create, topup_bonus and server_action.
What tools does the ServGhost MCP server have?
- 11 tools: 3 irreversible, 2 write, 6 read. topup_create, topup_bonus, server_action, quote, create_order, list_plans, list_locations, account_balance and 3 more.
Does the ServGhost MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the ServGhost MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): server_action.
Has the ServGhost MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 1, 2026.