TurboMax AI MCP server
com.turbomaxai/mcpturbomaxai.comstreamable-httpv1.0.0Scanned
Generate AI video, images and music, chat with LLMs, and manage a prepaid credits wallet.
13 tools: 1 can delete or cancel things, 1 do something that can't be undone, 4 change things and 7 only read.
- Reads private data · 1
- Reads text others write · 6
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things and 1 does something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the TurboMax AI MCP server can do
The TurboMax AI MCP server is published by turbomaxai.com, a domain the MCP Registry verified. It has 13 tools. It can delete or cancel things (1 tool: cancel_task), do things that cannot be undone, such as sending, paying or publishing (chat) and create or change data (4 tools: estimate_cost, generate_media, retry_task and upload_source_media). 7 tools only read.
1 tool reads private data (list_chat_models); 6 tools bring in text other people can write (generate_media, retry_task, upload_source_media and 3 more); 1 tool can send data out of your system (chat). 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.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 15, 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.
13 tools
Deletes or cancels 1Claude Code: deny
cancel_taskStop a job that is still processing and refund its hold.No findings
Why it is in this group
- The name "cancel_task" says "cancel": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Stop a job that is still processing and refund its hold. Requires a "generate" key.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
Can't be undone 1Claude Code: ask
chatSend one chat turn to a TurboMax text model and return its reply.Reads text others writeCan 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
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe description's first verb is "send": it sends or publishes something to other people.
Description, as the server wrote it Send one chat turn to a TurboMax text model and return its reply. SPENDS CREDITS (held, then settled to actual usage). Stateless: send the whole conversation in messages, or just message for a single question. Requires a "generate" key.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Changes things 4Claude Code: ask
estimate_costApproximate credits for a media generation from the live price list.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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Approximate credits for a media generation from the live price list. The exact amount is held when you call generate_media; pass maxCredits there to make it a hard ceiling.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
generate_mediaStart a generation.Reads text others writeNo findings
Why it is in this group
- The name "generate_media" says "generate": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Start a generation. SPENDS CREDITS from the wallet (held now, settled to the actual cost when the job ends; refunded if it fails). Returns a taskId immediately - follow it with get_task (waitSeconds) until completed. Use only the user's own prompt text. For image-to-video etc. upload the source first (upload_source_media). Requires an API key with the "generate" scope.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
retry_taskRe-run a failed or cancelled job as a new job.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Re-run a failed or cancelled job as a new job. SPENDS CREDITS again (a fresh hold). Requires a "generate" key.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
upload_source_mediaUpload an image, video or audio file (PNG, JPEG, WebP, GIF, MP4, WebM, MOV, MP3, WAV) to use as sourceImageUrl (or, for audio, sourceAudioUrl) in generate_media.Reads text others writeNo findings
Why it is in this group
- The name "upload_source_media" says "upload": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Upload an image, video or audio file (PNG, JPEG, WebP, GIF, MP4, WebM, MOV, MP3, WAV) to use as sourceImageUrl (or, for audio, sourceAudioUrl) in generate_media. Send the bytes as base64 (or a local filePath when this server runs locally). Requires a "generate" key.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 7Show 7 read-only tools
browse_galleryWork other users chose to publish, with the prompt and model used.Reads text others writeNo findings
Why it is in this group
- The name "browse_gallery" says "browse": a word for reading.
What it can reach
- untrusted-inputThe name "browse_gallery" says "browse": it reads web pages, which anyone can write.
Description, as the server wrote it Work other users chose to publish, with the prompt and model used. Public; anonymous.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_modelFull parameter details and pricing for one media model.No findings
Why it is in this group
- The name "get_model" says "get": a word for reading.
Description, as the server wrote it Full parameter details and pricing for one media model.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_taskStatus, progress and result of a job started with generate_media.No findings
Why it is in this group
- The name "get_task" says "get": a word for reading.
Description, as the server wrote it Status, progress and result of a job started with generate_media. With waitSeconds it waits for completion. resultUrl is a time-limited link - download or use it promptly. Polling also settles the wallet when the job ends.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_walletCredit balance, credits-per-dollar, today's usage against the account limits, and recent ledger entries.No findings
Why it is in this group
- The name "get_wallet" says "get": a word for reading.
Description, as the server wrote it Credit balance, credits-per-dollar, today's usage against the account limits, and recent ledger entries.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_chat_modelsThe text/chat models available to chat, with the default and whether each is currently available.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_chat_models" says "list": a word for reading.
What it can reach
- private-dataThe name "list_chat_models" says "list" and "chat": it reads messages.
- private-dataThe description's first sentence says "chat": it reads messages.
- untrusted-inputThe name "list_chat_models" says "list" and "chat": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "chat": it reads messages, which other people can write.
Description, as the server wrote it The text/chat models available to chat, with the default and whether each is currently available.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_generationsThe account's generation history, newest first, with status, cost and result links.No findings
Why it is in this group
- The name "list_generations" says "list": a word for reading.
Description, as the server wrote it The account's generation history, newest first, with status, cost and result links.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_modelsList the image, video and audio models with what each accepts (tasks, aspect ratios, resolutions, duration range, modes) and its price in credits.No findings
Why it is in this group
- The name "list_models" says "list": a word for reading.
Description, as the server wrote it List the image, video and audio models with what each accepts (tasks, aspect ratios, resolutions, duration range, modes) and its price in credits. Call this before generate_media; use the exact ids and values it returns.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: 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.
6 paths 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 write6
- 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__turbomaxai__chat"
]
}
}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 17, 2026, 15:22 UTC, unchanged since Nov 3, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 6
- Protocol version
- 2025-06-18
- 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (1 destructive, 1 irreversible, 4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://turbomaxai.com/mcp: tools/list returned 13 tools to an anonymous client, including cancel_task (destructive), chat (irreversible), estimate_cost (write), generate_media (write), retry_task (write) and 1 more
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.
Tools2 changed.~2 changedView diff
- Changed:generate_mediaChanges thingsinputSchema
- Changed:upload_source_mediaChanges thingsdescription
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http turbomaxai https://turbomaxai.com/mcpclaude mcp add --transport http turbomaxai https://turbomaxai.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__turbomaxai__list_models",
"mcp__turbomaxai__get_model",
"mcp__turbomaxai__get_task",
"mcp__turbomaxai__list_chat_models",
"mcp__turbomaxai__get_wallet",
"mcp__turbomaxai__list_generations",
"mcp__turbomaxai__browse_gallery"
],
"ask": [
"mcp__turbomaxai__estimate_cost",
"mcp__turbomaxai__generate_media",
"mcp__turbomaxai__retry_task",
"mcp__turbomaxai__upload_source_media",
"mcp__turbomaxai__chat"
],
"deny": [
"mcp__turbomaxai__cancel_task"
]
}
}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 turbomaxai. Review it before you use it.
Capability tags behind 6 rules
- mcp__turbomaxai__generate_media untrusted-input
- mcp__turbomaxai__retry_task untrusted-input
- mcp__turbomaxai__upload_source_media untrusted-input
- mcp__turbomaxai__list_chat_models private-data, untrusted-input
- mcp__turbomaxai__chat untrusted-input, outbound
- mcp__turbomaxai__browse_gallery untrusted-input
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.turbomaxai/mcp/verify?hash=d566aab2b982276e8fa00794855892882542f0a1fc8eb2365bb7facd7c969c36" | jq -e '.changed == false'Pinned hash d566aab2b982, from Nov 15, 2026, 17:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.turbomaxai/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.turbomaxai/mcp)Source: MCP Registry. Synced Nov 2, 2026, 11:17 UTC.
TurboMax AI MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the TurboMax AI MCP server safe?
- No scan can promise that. What its definitions show: 13 tools, 6 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 TurboMax AI MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: cancel_task.
Can the TurboMax AI MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: chat.
What tools does the TurboMax AI MCP server have?
- 13 tools: 1 destructive, 1 irreversible, 4 write, 7 read. cancel_task, chat, estimate_cost, generate_media, retry_task, upload_source_media, list_models, get_model and 5 more.
Does the TurboMax AI MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the TurboMax AI 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): chat.
Has the TurboMax AI MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.