Skip to content

MCP servers › studio.ai3d › ai3d-studio

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

studio.ai3d/ai3d-studio

Generate 3D models from images or text with AI, then retexture or convert them to STL, 3MF or OBJ. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-10-23Topic: media-and-design · AI-classifiedversion 1.0.0streamable HTTP14 tools

Summary

studio.ai3d/ai3d-studio is a remote MCP server listed in the official MCP registry at version 1.0.0. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 14 tools, 1 resource and 0 prompts.

Record checks

1 of 2 record checks met · 7 do not apply

  • met: Registry entry is active and says how to run it
  • not met: Source repository link opens
  • not applicable: Repository is not archived
  • not applicable: Code pushed to the repository in the 90 days before our check
  • not applicable: Repository publishes a security policy (SECURITY.md)
  • not applicable: Package names its licence with a standard (SPDX) identifier
  • not applicable: The version the registry lists can be installed and is not withdrawn
  • not applicable: npm package carries build provenance (attestation)
  • not applicable: No known critical or high advisory in the package or its dependencies
  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Key facts

Runs
remote (hosted by the publisher)
Transport
streamable HTTP
Sign-in
none needed to open a session
Tools
14
Described as changing data
5 of 14 toolsAI-classified
Mainly works on
files and code on the machine it runs on; accounts and data in outside web servicesAI-classified
Topic
media-and-designAI-classified
Last tested
2026-10-23

Add to your client

Worth knowing before you connect it

  • 5 tools are described as changing something (generate_3d, generate, start_batch, …): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-10-23
Mode
read-only (no tool calls)
Latest version
1.0.0, published 2026-10-08 (registry, as of the 2026-10-23 snapshot)
First listed version
2026-10-08 (earliest version still in the registry; older removed versions would be earlier)
Registry data
snapshot 2026-10-23
Package and repository
checked 2026-10-23
Engine
mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 1.0.0 (published 2026-10-08).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory
14tools
1resources
0prompts

What it mainly works on, as our AI model read its tool descriptions: files and code on the machine it runs on; accounts and data in outside web services.

5 of 14 tools are described as changing something (creating, editing, deleting, sending or running).

  • list_modelson 94 other serversreads or searches

    “List the models this account can generate with, grouped by what they make (3D, image, …): each with its id, the scenes (input modes such as text-to-3d or image-to-3d) it supports, and the credits it …”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    3 inputs
    • media_typestring“Only models of this kind, e.g.”
    • available_onlyboolean“Leave out models that are listed but cannot be started.”
    • include_inputsboolean“Include the option fields of every scene (larger result).”
  • estimate_coston 48 other serversreads or searches

    “Price a generation before starting it: the credits this model would charge for these options, and whether the current balance covers it.”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    4 inputs, 1 required
    • modelstringrequired“A model id from list_models.”
    • scenestring“A scene id from list_models, e.g.”
    • promptstring
    • optionsobject“The options you intend to pass; they change the price.”
  • get_balanceon 101 other serversreads or searches

    “Get the credits this account can spend now (and how many of them come from the subscription or are permanent), the plan name when there is one, and — when you are connected with an API key that has a…”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    Takes no inputs.

  • generate_3don 1 other serverdescribed as changing data

    “Start a 3D generation and return its job id at once.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    6 inputs, 2 required
    • modestringrequired“Which input the model is given.”
    • modelstringrequired“A 3D model id from list_models.”
    • promptstring
    • optionsobject“Model-specific options; take the field names from list_models with include_inputs, and price them with estimate_cost first.”
    • expected_creditsinteger“The credits estimate_cost answered for this request.”
    • idempotency_keystring“Reuse the same value when retrying this exact request.”
  • generateon 19 other serversdescribed as changing data

    “Start an async AI generation of any media type and return its job id.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    8 inputs, 2 required
    • mediaTypestringrequired“Generation family, e.g.”
    • modelstringrequired
    • promptstring“The prompt; with options.preset, only your additional instructions.”
    • optionsobject“Model-specific options; derive from list_models (include_inputs).”
    • scenestring
    • workflowTypestring
    • expectedCreditsinteger“The credits estimate_cost answered for this request.”
    • idempotencyKeystring
  • get_jobon 138 other serversreads or searches

    “Get a job started by generate_3d or generate: its status, progress, credits charged and refunded, and — when it has finished — the result files with their public download URLs, including other format…”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • job_idstringrequired“The job id returned by generate_3d or generate.”
  • list_job_filesreads or searches

    “List the files a finished job already has, one per format: the main result plus any alternate formats the model returned (for 3D models, for example glb with fbx or usdz), each with a public download…”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 1 required
    • job_idstringrequired“The job id returned by generate_3d or generate.”
    • formatstring“A file format to look for, e.g.”
  • start_batchdescribed as changing data

    “Run the same model, scene and options once for each of several pictures in the account’s Library — for example image to 3D for twelve product photos.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    9 inputs, 3 required
    • modelstringrequired
    • scenestringrequired
    • optionsobject“Options every run shares, as for generate; the picture field is filled per item.”
    • promptstring
    • itemsarrayrequired“One entry per picture: a Library image’s asset_id.”
    • project_idstring
    • notify_by_emailboolean
    • expected_creditsinteger“The quote you showed the person; a different price queues nothing.”
    • idempotency_keystring
  • list_batcheson 5 other serversreads or searches

    “The account’s batches of one scene from the last 24 hours, newest first, with each picture’s progress — and how many pictures its plan lets one batch hold (allowance; 0 means the plan includes no bat…”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    2 inputs, 1 required
    • scenestringrequired
    • limitinteger
  • get_batchon 5 other serversreads or searches

    “The state of a batch and of each picture in it: queued, running, done, failed or cancelled, the job_id of its run once started (get_job gives the files), credits charged, and whether retry_batch can …”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • batch_idstringrequired“The batch id start_batch returned.”
  • retry_batchdescribed as changing data

    “Queue the batch’s failed pictures (and any stopped for want of credits) again as new runs, or only the item_ids given.”

    Publisher declares: read-only no · destructive no · idempotent no · open-world yes

    2 inputs, 1 required
    • batch_idstringrequired“The batch id start_batch returned.”
    • item_idsarray
  • search_libraryon 22 other serversreads or searches

    “Search the Library of past generations kept by this account, newest first: filter by words in the prompt or title and by kind (3d, image, …).”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    4 inputs
    • querystring“Words to look for in the prompt or title.”
    • media_typestring“Only runs of this kind, e.g.”
    • limitinteger“How many to return, 1 to 50.”
    • cursorstring“The next_cursor of the previous result.”
Show 2 more tools
  • convert_modelcreates or changes datadescribed as changing data

    “Convert one of the account’s Library 3D models (a GLB) to GLB, STL, 3MF, OBJ or PLY on the server, optionally simplifying it, compressing its geometry, scaling it to a real-world size, moving its ori…”

    Publisher declares: read-only no · destructive no · idempotent yes · open-world no

    10 inputs, 1 required
    • asset_idstringrequired“A GLB file of one of your Library models.”
    • formatstring“The file to make; glb when omitted.”
    • compressionstring“GLB only: meshopt (default, smallest) or none.”
    • simplifynumber“Share of triangles to keep: 1 (default), 0.75, 0.5 or 0.25.”
    • resize_heightnumber“Scale the model to this height, in metres.”
    • resize_longest_sidenumber“Scale the model so its longest side is this long, in metres.”
    • originstring“Move the origin to the bottom centre (default when resizing) or the centre.”
    • repairboolean“Repair for printing first: weld, drop broken and duplicate faces and loose debris, fix flipped faces, fill holes.”
    • namestring
    • project_idstring
  • viewer_job_statereads or searches

    “Used by the interactive 3D viewer shown next to a generation result, not for direct use: the state of one job and, once it has finished, the URL of the model file the viewer can draw plus the downloa…”

    Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

    1 input, 1 required
    • job_idstringrequired“The job id returned by generate_3d.”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

Says what the tool does
100% of 14 tools
Says what it returns
100% of 13 tools
Says when to use it
100% of 10 tools
Items covered per tool
4.0 of 4 on average

Counted from the listing

Parameters with a description
68% of 53
Tools with a description
100% of 14
Typical description length
433 characters

The tool set

Counted from the listing

Tools
14
Size of the list
about 12,384 tokens for an agent to load (characters ÷ 4)
Naming
13 of 14 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 14 of 14 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-10-23 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste:
https://ai3d.studio/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "ai3d-studio": {
      "url": "https://ai3d.studio/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "ai3d-studio": {
      "type": "http",
      "url": "https://ai3d.studio/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"ai3d-studio","type":"http","url":"https://ai3d.studio/mcp"}'
Claude Code
claude mcp add --transport http ai3d-studio https://ai3d.studio/mcp
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://ai3d.studio/mcp --transport http
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry saysWe foundResultSource · date
Remote endpoint ai3d.studio/mcpSession openedmatchesour test · 2026-10-23
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-10-23

Choosing

Record checks

Public records · not a safety rating

1 of 2 record checks met · 7 do not apply

  • Not ranked by downloads: a remote server publishes no download figure
  • Not ranked by stars: no public GitHub repository
  • MetRegistry entry is active and says how to run itActive, with a package or a remote address.
  • Not metSource repository link opensThe registry entry gives no repository link.
  • Does not applyRepository is not archivedNo public GitHub repository to read.
  • Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
  • Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
  • Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
  • Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
  • Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
  • Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about studio.ai3d/ai3d-studio

Answered from the data above

Is studio.ai3d/ai3d-studio safe to install?

We do not rate servers as safe or unsafe. 1 of its 2 applicable record checks are met (facts from public records, each listed on this page). What the records show: 5 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Does studio.ai3d/ai3d-studio need an API key or sign-in?

It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.

Has studio.ai3d/ai3d-studio been security tested?

Partly. 4 of the 15 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security verdict is published before verification.

What can studio.ai3d/ai3d-studio do?

It lists 14 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search and create or change data. We did not call any tool, so this describes the text, not the behaviour.

Can studio.ai3d/ai3d-studio change or delete data?

5 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Similar servers

Same topic · AI-read

Active servers whose topic is also “media-and-design” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Not probed (we call no server's tools)

We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: exercised
  13. Fake assistant turns: not applicable
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. Sign-in metadata: exercised

4 exercised11 not run (reason given)3 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 4 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 4
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.exercised
  • 12Hidden content
    audience-hiding
    Checks resources that hide content from the user.exercised
  • 18Sign-in metadata
    oauth-url-scheme
    Checks the published sign-in metadata for unsafe URLs.exercised
Not run, with the reason · 11
  • 3Real execution
    real-execution
    Calls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 4Secret leak
    canary-leak
    Plants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 5Internal addresses
    ssrf
    Checks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 6Unconfirmed changes
    write-without-confirmation
    Checks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 7Bad input
    error-handling
    Sends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 8Model requests
    sampling
    Checks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 9Sensitive questions
    elicitation-sensitive-data
    Checks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 10Folder boundary
    root-boundary
    Checks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 11Log leaks
    logging-side-channel
    Checks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 16Sign-in redirect
    open-redirect
    Checks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
  • 17Consent handling
    confused-deputy
    Checks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
Does not apply to this server · 3
  • 13Fake assistant turns
    fake-assistant-turn
    Checks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
  • 14Token passthrough
    token-passthrough
    Checks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 15Token audience
    token-audience-validation
    Checks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable

Source: our own test, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 4,152 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 14 tools, 1 resource, 0 prompts.
  4. 13,113 msFinished: 4 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified
AI-classified · 2026-10-23
Pricing modelAI-classified
no value
No value: the AI answer was held back because the quoted text did not clearly support it.
Programming language
does not apply
no existing GitHub repository (server declares no repository link, so there is nothing to fetch)
Hosting type
registry · 2026-10-23
MCP capability
resources, tools
our test · 2026-10-23
Transport
streamable HTTP
registry · 2026-10-23
Required credentials
none declared
registry · no declaration is not a guarantee
Package registry
does not apply
remote-only server: no package is shipped, so there is no package registry
Freshness
0–30 days
registry updatedAt · 2026-10-23
Lifecycle status
registry · 2026-10-23
License class
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Integrity hash
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Signature / provenance
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Dependency advisories
does not apply
ships no package, so there are no dependencies to audit
Popularity
does not apply
remote-only server: ships no package, so there is nothing to look up in a package registry
Publisher signals
not stated
no readable GitHub owner to describe
Maintenance
does not apply
server declares no repository link, so there is nothing to fetch
Environment
the publisher's infrastructure
where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “studio.ai3d/ai3d-studio: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/studio.ai3d/ai3d-studio

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

ProtocolProbe: 1 of 2 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/studio.ai3d/ai3d-studio)](https://protocolprobe.com/mcp/servers/studio.ai3d/ai3d-studio)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology