Fractera MCP server
io.github.Fractera/deployFracterastreamable-httpv1.0.0Scanned
Zero-Ops deploy of a private AI workspace to your own VPS — from your AI chat. Free and open-source.
6 tools: 2 can delete or cancel things and 4 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
The remote endpoint did not answer the last look. Remote posture
Anlyon alternative
2 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 Fractera MCP server can do
The Fractera MCP server is published by the GitHub account Fractera. It has 6 tools. It can delete or cancel things (2 tools: register_and_deploy and retry_deploy). 4 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Last scanned Nov 3, 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.
6 tools
Deletes or cancels 2Claude Code: deny
register_and_deployRegister a new Fractera user and start the deployment of their server in one atomic call.No findings
Why it is in this group
- The name "register_and_deploy" says "deploy": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Register a new Fractera user and start the deployment of their server in one atomic call. Use this AFTER you have collected the user's email (entered twice for typo protection), server IP, and root password. Creates the User row (or reuses an existing one with the same email), creates a free Subscription, creates a ServerToken, wipes any previous installation on the target server, and launches bootstrap. The deploy is IP-first (phase-1): the server comes up on plain HTTP at http://<IP>:3002 in 8-14 minutes; it does NOT get a domain or HTTPS cert here (that is an optional later step inside the workspace). Returns session_id (for a single on-demand check_status read — do not poll) and server_token (so the user can recover via retry_deploy if anything breaks). Call this AT MOST ONCE per conversation.
Annotations the server declares
- destructiveHint: true
- readOnlyHint: false
retry_deployRetry a failed deployment using a server_token (from the failure email, the deploy-progress UI, or the dashboard).No findings
Why it is in this group
- The name "retry_deploy" says "deploy": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Retry a failed deployment using a server_token (from the failure email, the deploy-progress UI, or the dashboard). Wipes the previous broken install and runs a fresh deploy on the SAME server. Returns a new session_id — poll with check_status. Use this when the user reports a failed deploy or pastes a server_token.
Annotations the server declares
- destructiveHint: true
- readOnlyHint: false
Only reads 4Show 4 read-only tools
check_statusRead the current installation progress ONCE, on demand.No findings
Why it is in this group
- The name "check_status" says "status": a word for reading.
Description, as the server wrote it Read the current installation progress ONCE, on demand. Call this only when the user explicitly asks how the deploy is going (e.g. "what is the status", "did it finish") — never on a timer and never in a polling loop. The deploy takes 8-14 minutes and the authoritative status channels are the email pipeline + the dashboard; one read on request is enough. Returns the current step, the list of completed steps (~44 total in a full bootstrap), and whether installation is done or failed.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
get_project_infoProject reference / help desk about Fractera.No findings
Why it is in this group
- The name "get_project_info" says "get": a word for reading.
Description, as the server wrote it Project reference / help desk about Fractera. Use this to answer ANY user question about what Fractera is, how it works, its architecture, components, modes, data ownership, pricing, use cases, partner program, etc. — especially while a deploy is running and the user wants to learn more. TOKEN-ECONOMY: call with NO arguments first to get the lightweight list of section ids+titles, then call again with a single `section` id to fetch just that section. NEVER try to fetch everything at once; pull only the section(s) relevant to the user question. Set `lang:"ru"` for Russian-speaking users.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
get_subdomainReturn the final entry address of the server once installation is complete.No findings
Why it is in this group
- The name "get_subdomain" says "get": a word for reading.
Description, as the server wrote it Return the final entry address of the server once installation is complete. In phase-1 (IP-first) this is a plain-HTTP Admin URL of the form http://<IP>:3002 — the server has NO domain and NO HTTPS cert yet (attaching a custom domain with HTTPS is an optional later step the user does inside Admin -> Personal Domain). Call this once after check_status reports status="done".
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
get_vps_recommendationReturn a single recommended VPS provider for users who do not yet have a server.No findings
Why it is in this group
- The name "get_vps_recommendation" says "get": a word for reading.
Description, as the server wrote it Return a single recommended VPS provider for users who do not yet have a server. Call this ONLY when the user explicitly says they have no server. The user buys the VPS at this provider and comes back with IP + password.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
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, 18:58 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- no
- HTTP status of an anonymous initialize
- not observed
- 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: www.fractera.ai does not resolve.
Posture changes
- Nov 20, 2026
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 2 to 0
- Protocol version: 2024-11-05 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. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 2 more).View diff
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 2 to 0
- Protocol version: 2024-11-05 to none
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http deploy https://www.fractera.ai/api/mcpclaude mcp add --transport http deploy https://www.fractera.ai/api/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__deploy__check_status",
"mcp__deploy__get_subdomain",
"mcp__deploy__get_vps_recommendation",
"mcp__deploy__get_project_info"
],
"ask": [],
"deny": [
"mcp__deploy__register_and_deploy",
"mcp__deploy__retry_deploy"
]
}
}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 deploy. Review it before you use it.
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/io.github.Fractera/deploy/verify?hash=cb0941f62e1a573ca00d6a0167dad5885fa53381e18776e80c8b96292481ea1b" | jq -e '.changed == false'Pinned hash cb0941f62e1a, from Nov 3, 2026, 07:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Fractera/deploy/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Fractera/deploy)Source: MCP Registry. Synced Oct 21, 2026, 18:16 UTC.
Fractera MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Fractera MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 2 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 Fractera MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: register_and_deploy and retry_deploy.
Can the Fractera MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Fractera MCP server have?
- 6 tools: 2 destructive, 4 read. register_and_deploy, retry_deploy, check_status, get_subdomain, get_vps_recommendation and get_project_info.
Does the Fractera MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the Fractera MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Fractera MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 3, 2026.