Skip to content
actionlake
Start free

Connectors · AI

Stability AI Platform MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Stability AI Platform and the rest of your systems. It gives your agent 8 Stability AI Platform actions (7 reads and 1 write) and holds the Stability AI Platform credential itself, so the agent never does. It paces Stability AI Platform's limits and records every call.

Connect Stability AI Platform freeSee pricing

100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.

claude mcp add --transport http actionlake https://connect.actionlake.com/mcp
the first call
do {  action: "stability_ai.engines.list",  intent: "check which Stability AI Platform account is connected"}# List engines (v1) · read · 1 upstream call
  • 8actionsin one signed file
  • 7readlook, never change
  • 1writecreate and update
  • 0wait for a yesdestructive, confirmed first

Set up

Connect Stability AI Platform in three steps.

  1. 01

    Add actionlake to Claude.

    Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.

    https://connect.actionlake.com/mcp
  2. 02

    Connect Stability AI Platform.

    Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.

    • api_keyStability AI API key: platform.stability.ai > Account > API Keys (https://platform.stability.ai/account/keys)
    account { op: "connections.requirements", service: "stability_ai" }
# free: exactly what to paste, and what is found for you
  3. 03

    Make the first call. Check before a write.

    Ask in plain words; Claude picks the action. Before anything changes, check validates the call and prices it, for free.

    do    { action: "stability_ai.engines.list" }# list engines (v1) · read · 1 upstream callcheck { action: "stability_ai.sdxl_images.text_to_image", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Stability AI Platform at a glance

Sign-in
Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
You provide
api_key
Limits we pace to
150 calls per 10 seconds, per connection
API covered
Stability AI Platform API (SDXL text-to-image, engines, async generation results, account and credit balance) API Stability AI REST v2beta / v2alpha (OpenAPI 3.0.1) and v1api.stability.ai
Built from
Stability AI Platform's documentation, read 23 October 2026docs.stability.aidocs.stability.ai
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
3 of 7 reads, for up to 5 minutes; a write clears what it affects
Shared entities
1, so ask can line Stability AI Platform up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Stability AI Platform.

8 actions in 8 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 7readlook, never change
  • 1writecreate and update
  • 0destructivewait for a confirmation

  1. Account

    1

    1 read · 0 write · 0 destructive

    Get account details

  2. Audio results

    1

    1 read · 0 write · 0 destructive

    Fetch an async audio generation result

  3. Balance

    1

    1 read · 0 write · 0 destructive

    Get credit balance

  4. Creative upscale results

    1

    1 read · 0 write · 0 destructive

    Fetch a creative upscale result

  5. Engines

    1

    1 read · 0 write · 0 destructive

    List engines (v1)

  6. Results

    1

    1 read · 0 write · 0 destructive

    Fetch an async generation result

  7. SDXL images

    1

    0 read · 1 write · 0 destructive

    Generate an image from text (SDXL 1.0, v1)

  8. Upscale results v2alpha

    1

    1 read · 0 write · 0 destructive

    Fetch an upscale result (v2alpha)

Top actions

The Stability AI Platform API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems.

ActionWhat it doesEffectSame name in
stability_ai.account.getGet account detailsGet account details.readthis connector
stability_ai.engines.listList engines (v1)List engines (v1).readthis connector
stability_ai.sdxl_images.text_to_imageGenerate an image from text (SDXL 1.0, v1)Generate an image from text (SDXL 1.0, v1).writethis connector
stability_ai.balance.getGet credit balanceGet credit balance.readthis connector
stability_ai.results.getFetch an async generation resultFetch an async generation result.readthis connector
stability_ai.audio_results.getFetch an async audio generation resultFetch an async audio generation result.readthis connector
stability_ai.upscale_results_v2alpha.getFetch an upscale result (v2alpha)Fetch an upscale result (v2alpha).readthis connector
stability_ai.creative_upscale_results.getFetch a creative upscale resultFetch a creative upscale result.readthis connector

Try it

Prompts to paste into Claude.

Each one names the Stability AI Platform actions it will call, so you know what it reads and what it changes before you send it.

  1. Readread

    List engines (v1) in Stability AI Platform and tell me what stands out.

    callsstability_ai.engines.list

  2. Writewrite

    Generate an image from text (SDXL 1.0, v1) in Stability AI Platform. Show me exactly what you will send before you save it.

    callsstability_ai.sdxl_images.text_to_image

Governance for Stability AI Platform

Every write can wait for a yes.

None of Stability AI Platform's actions is destructive. A key can still be held to reads, capped, and set so a person confirms every write.

A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.

a key for this connector
account {  op: "keys.create", name: "stability-ai-agent",  allowed_actions: ["stability_ai.*"], cap_calls: 2000,  confirm_policy: "human_for_writes"}
Illustrative. Scoped to Stability AI Platform only, capped at 2,000 upstream calls, every write confirmed.

Cost

What Stability AI Platform costs on actionlake.

Every Stability AI Platform action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Stability AI Platform refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

  • 1upstream call per actionall 8 Stability AI Platform actions
  • 8actions pageeach page of a long list is one call
  • 3reads can be cacheda cache hit costs nothing
  • 100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every Stability AI Platform action.

8 actions by area: the id your agent calls, what it does, and its effect.

Account1
  • stability_ai.account.getGet account detailsread
Audio results1
  • stability_ai.audio_results.getFetch an async audio generation resultread
Balance1
  • stability_ai.balance.getGet credit balanceread
Creative upscale results1
  • stability_ai.creative_upscale_results.getFetch a creative upscale resultread
Engines1
  • stability_ai.engines.listList engines (v1)read
Results1
  • stability_ai.results.getFetch an async generation resultread
SDXL images1
  • stability_ai.sdxl_images.text_to_imageGenerate an image from text (SDXL 1.0, v1)write
Upscale results v2alpha1
  • stability_ai.upscale_results_v2alpha.getFetch an upscale result (v2alpha)read

Questions

The Stability AI Platform MCP server, answered.

Is there a Stability AI Platform MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 8 Stability AI Platform actions across account, audio results, balance and creative upscale results, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Stability AI Platform.

What do I need to connect Stability AI Platform?

Stability AI API key: platform.stability.ai > Account > API Keys (https://platform.stability.ai/account/keys). The free call account { op: "connections.requirements", service: "stability_ai" } lists exactly what to paste.

Can an AI agent change things in Stability AI Platform?

Only if its key allows it. 1 Stability AI Platform action write, and none is destructive. A key can be limited to reads, capped, and set so a person confirms every write.

Will an AI agent use up my Stability AI Platform API limit?

actionlake paces every call to the limits in the Stability AI Platform service file: 150 calls per 10 seconds per connection. Repeated reads are answered from cache (3 Stability AI Platform actions can be), which never reaches Stability AI Platform.

What does a Stability AI Platform action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (8 Stability AI Platform actions page). Cache hits, searches, dry runs and calls Stability AI Platform refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

Which Stability AI Platform API does it cover?

The Stability AI Platform API (SDXL text-to-image, engines, async generation results, account and credit balance) API Stability AI REST v2beta / v2alpha (OpenAPI 3.0.1) and v1 at api.stability.ai. It is built from Stability AI Platform's documentation as read on 23 October 2026. 8 actions in 8 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Stability AI Platform data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Stability AI Platform credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.

Which AI clients can use it?

Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.

More connectors like Stability AI Platform

Joins with, on shared entities

Browse

actionlake is independent. It is not made or endorsed by Stability AI Platform; the name is the vendor's own. Counts are from the Stability AI Platform service file, version 1.0.0.

Give your agent Stability AI Platform today.

Connect Stability AI Platform freeSee pricing

Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.