Atlas / MCP servers / tadasant / Stability AI

Stability AIBLOCK

mcp/tadasant/stability-ai

MCP Server integrating MCP Clients with Stability AI-powered image manipulation functionalities: generate, edit, upscale, and more.

Verdict
BLOCK
Grade
D
Trust score
69 /100
Exposed tools
20 18r · 1w · 1d
Transport
sse · stdio
License
MIT
Stars
84
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Stability AI MCP Server

Haven't heard about MCP yet? The easiest way to keep up-to-date is to read our weekly newsletter at PulseMCP.

This is an MCP (Model Context Protocol) Server integrating MCP Clients with Stability AI's latest & greatest Stable Diffusion image manipulation functionalities: generate, edit, upscale, and more.

Stability AI is a leading AI model provider and this server connects directly to their hosted REST API. You will need to sign up for an API Key from stability.ai to get started.

They provide 25 credits for free. Afterward, pay-as-you-go pricing is very reasonable: $0.01/credit, where 3 credits gets you an image generation on their Core model. So 100 high quality images = just $3.

This project is NOT officially affiliated with Stability AI.

Demo video, and a teaser here:

Read from source at commit 600be5bf47adOBSERVED · 2026-10-07
Advertisement
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add mcp-server-stability-ai --env GCS_PRIVATE_KEY=${GCS_PRIVATE_KEY} --env STABILITY_AI_API_KEY=${STABILITY_AI_API_KEY} -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "mcp-server-stability-ai": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "GCS_PRIVATE_KEY": "${GCS_PRIVATE_KEY}",
        "STABILITY_AI_API_KEY": "${STABILITY_AI_API_KEY}"
      }
    }
  }
}
03

Exposed tools (20)

18 read · 1 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

ToolRiskDescription
edit-imagewriteMake a minor modification to an existing image
generate-image-from-sketchreadGenerate an image from a hand-drawn sketch
generate-image-from-textreadGenerate a new image with configurable description, style, and aspect ratio
generate-image-in-the-style-ofreadGenerate an image in the style of an existing image
generate-image-using-structurereadGenerate an image while maintaining the structure (i.e. background, context) of a reference image
stability-ai-0-list-resourcesreadUse this to check for files before deciding you don
stability-ai-control-sketchreadTranslate hand-drawn sketches to production-grade images.
stability-ai-control-structurereadGenerate a new image while maintaining the structure of a reference image
stability-ai-control-stylereadGenerate a new image in the style of a reference image
stability-ai-generate-image-corereadGenerate an image using Stability AI
stability-ai-generate-image-sd35readGenerate an image using Stable Diffusion 3.5 models with advanced configuration options.
stability-ai-generate-image-ultrareadGenerate an image using Stability AI
stability-ai-outpaintreadExtends an image in any direction while maintaining visual consistency.
stability-ai-remove-backgrounddestructiveRemove the background from an image.
stability-ai-replace-background-and-relightreadReplace background and adjust lighting of an image
stability-ai-search-and-recolorreadSearch and recolor object(s) in an image
stability-ai-search-and-replacereadReplace objects or elements in an image by describing what to replace and what to replace it with.
stability-ai-upscale-creativereadEnhance image resolution up to 4K using AI with creative interpretation. This tool works best on highly degraded images and performs heavy reimagining. In general, don
stability-ai-upscale-fastreadCheap and fast tool to enhance image resolution by 4x.
upscale-imagereadUpscale the quality of an image
04

Trust audit

BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeFAIL
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
declared (5 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
found

Findings (7)

CRITICALHard-coded secrets · secret.private_key · CWE-798, CWE-321
src/gcs/gcsClient.ts:6
// GCS_PRIVATE_KEY=-----BEGIN PRIVATE KEY-----\nYourKeyHere\n-----END PRIVATE KEY-----\n
MEDIUMHard-coded secrets · secret.private_key · CWE-798, CWE-321
README.md:178
| `GCS_PRIVATE_KEY`         | Google Cloud Service Account private key for storing images                                               | N (Y if using SSE) | N/A
MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59
stability-ai-remove-background
Why it matters. 1 tool(s) can delete or overwrite
Fix. prefer a read-only mode or scoped tokens; the page states the blast radius
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@google-cloud/storage, @modelcontextprotocol/sdk, axios, body-parser, dotenv, express, open, zod
Why it matters. 12 dependency range(s) float
Fix. pin exact versions or ship a lockfile
INFOInventory / provenance · inv.oversize · CWE-1104
images/mcp-server-stability-ai-logo.png
images/mcp-server-stability-ai-logo.png
Why it matters. 1384674 bytes not read
INFOInventory / provenance · inv.oversize · CWE-1104
images/teaser.gif
images/teaser.gif
Why it matters. 12648634 bytes not read
INFOPrompt injection · prompt.fetch_and_trust · CWE-94, CWE-1427
README.md:192
Then proceed to your preferred method of configuring the server below. If this is your first time using MCP Servers, you'll want to make sure you have the [Claude Desktop application](https://claude.a
Why it matters. remote text is to be obeyed as instructions

Gates applied: critical_finding, no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha 600be5bf47adfull audit observations/trust-audit/mcp-server/tadasant__stability-ai.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-07600be5bf47adBLOCKD69first audit
06

Questions

What is the Stability AI MCP server?

MCP Server integrating MCP Clients with Stability AI-powered image manipulation functionalities: generate, edit, upscale, and more.

What tools does Stability AI expose?

20 in total: 18 read-only, 1 that write, and 1 that can delete or overwrite (stability-ai-remove-background). Every one is listed on this page with its risk.

Is Stability AI safe to connect to an agent?

No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does Stability AI need?

It reads GCS_PRIVATE_KEY and STABILITY_AI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Stability AI run?

It speaks sse and stdio, so it runs as a local process your client starts. It is published on npm as mcp-server-stability-ai at 0.3.0.

How current is this page?

The grade is for one exact copy of the source (600be5bf47ad), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement