Cloudinary Analysis MCP (official)

70/100

Capped at 70: no passing tool call yet; the tests add up to 100. Why scores are capped

Last tested 2026-11-12 (Fresh: tested within 30 days) Connects · tools listedNo tool call tested yet Connects without a key; tool calls need one

Advisories: not yet checked

Security review: not tested

Test points add up to 100; the score is capped at 70 until a tool call passes. Not a quality or security rating. Methodology

Test points before the cap (100/100)

  • Install20/20
  • Handshake30/30
  • Maintenance25/25
  • Docs15/15
  • License10/10

Tested npm @cloudinary/analysis-mcp 0.5.3 (Cloudinary's Analyze API MCP, Public Beta; MIT; repo cloudinary/analysis-mcp). Launched as documented with `start`: initialize and tools/list over stdio succeeded with no credentials and listed 16 tools (AI Vision tagging/moderation/general, captioning, content-aware detection models, Google tagging/logo detection, image quality, watermark detection, task status). No tool was called: every analysis needs Cloudinary API credentials (or OAuth) and most need a paid add-on subscription, and we use no keys. Cloudinary's docs say its hosted Analysis server (analysis.mcp.cloudinary.com) uses OAuth only; we probed that endpoint too and got HTTP 401. Core tools not tested: 70 cap.

Transport (tested 2026-11-12): stdio

Token cost (estimate): approx. 4310 tokens, cl100k estimate (16 tools, measured 2026-11-12, version 0.5.3). This is an estimate from our testing of the tool names, descriptions and input schemas, counted with cl100k_base.

Permissions: 1 read, 0 write (state-changing), 15 unclassified · Auth: none · Rate limit: unknown · Pricing unit: unknown

Auth: none. Rate limit: unknown. Pricing unit: unknown.

  • analyze-ai-vision-general — unclassified
  • analyze-ai-vision-moderation — unclassified
  • analyze-ai-vision-tagging — unclassified
  • analyze-captioning — unclassified
  • analyze-cld-fashion — unclassified
  • analyze-cld-text — unclassified
  • analyze-coco — unclassified
  • analyze-google-logo-detection — unclassified
  • analyze-google-tagging — unclassified
  • analyze-human-anatomy — unclassified
  • analyze-image-quality — unclassified
  • analyze-lvis — unclassified
  • analyze-shop-classifier — unclassified
  • analyze-unidet — unclassified
  • analyze-watermark-detection — unclassified
  • tasks-get-status — read

handshake and tools listed without a recorded key or OAuth

Score 70/100 · Tools 16 · Token cost approx. 4,310 tokens · Compare · Last tested 2026-11-12 · Version tested 0.5.3 · Package @cloudinary/analysis-mcp · Repo cloudinary/analysis-mcp

Summary: Cloudinary Analysis MCP (official) completed an MCP handshake without credentials and exposed 16 tools.

Evidence summary

Handshake
pass
Tools listed
16
Context cost
approx. 4310 tokens, cl100k estimate (16 tools, measured 2026-11-12, version 0.5.3; an estimate) ranking · add up your servers' context cost
API key
Connects without a key; tool calls need one
Tested
2026-11-12

Test results

TestResultPointsEvidence
installpass20npm install @cloudinary/analysis-mcp (Node 20, Linux) succeeded in 2s.
handshakepass30MCP initialize + tools/list over stdio succeeded with no credentials; 16 tools listed in 8.6s.
maintenancepass25Repo pushed 0 days before test; 0 GitHub stars.
docspass15README over 3,000 chars; install instructions present; mcpServers config example present. Check of the package's own README (README shipped in npm package).
licensepass10MIT (OSI-approved).

Local-model readiness

Token cost (estimate): approx. 4310 tokens, cl100k estimate for 16 tools · about 53% of an 8k context. This is an estimate from our testing (counted with cl100k_base).

Small-model friendly (schema heuristic, not a model result): unknown.

Not tested

Small-model task runs: Not yet tested.

What we tested and what we didn't

Tested on 2026-11-12

  • Install from the registry
  • We connected with no credentials and asked for its tool list: it listed 16 tools (Method details: MCP initialize then tools/list)
  • Maintenance signals (last push, archived/deprecated status)
  • Docs (README length, install and config example)
  • License (OSI-approved or not)
  • Token cost (estimate)

Not tested

  • Security: not audited (no code review, no permission or data-flow analysis)
  • Real tasks (no functional task runs yet)
  • Behaviour with real credentials or a real account
  • Performance, rate limits or load
  • Correctness of results beyond the listed tasks

Methodology: how we test. A high score means it installs and responds, not that giving it access to your data carries no risk.

Known security issues

Not yet checked.

Monthly roundup: MCP security issues, October 2026.

Tool list changes

Baseline recorded from the 2026-11-12 test run; changes appear after the next test.

Snapshot hash (fingerprint of the tool list)

d0b920adc3b3: SHA-256 of the canonical tool names, descriptions and input schemas. If it changes, the tool list changed.

Feeds: RSS · JSON.

Raw test record (JSON)
{
  "name": "@cloudinary/analysis-mcp",
  "version": "0.5.3",
  "registry": "npm",
  "status": "working",
  "tested": "2026-11-12",
  "tools_count": 16,
  "deprecated": false,
  "archived": false,
  "tests": {
    "install": [
      "pass",
      20,
      "`npm install @cloudinary/analysis-mcp` (Node 20, Linux) succeeded in 2s."
    ],
    "handshake": [
      "pass",
      30,
      "MCP `initialize` + `tools/list` over stdio succeeded with no credentials; 16 tools listed in 8.6s."
    ],
    "maintenance": [
      "pass",
      25,
      "Repo pushed 0 days before test; 0 GitHub stars."
    ],
    "docs": [
      "pass",
      15,
      "README over 3,000 chars; install instructions present; `mcpServers` config example present. Check of the package's own README (README shipped in npm package)."
    ],
    "license": [
      "pass",
      10,
      "MIT (OSI-approved)."
    ]
  }
}

Install

npx -y @cloudinary/analysis-mcp start

Pin the version we tested

npx -y @cloudinary/analysis-mcp@0.5.3 start

tested 2026-11-12. Newer versions may differ and were not tested by us.

{
  "mcpServers": {
    "cloudinary-analysis-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@cloudinary/analysis-mcp@0.5.3",
        "start"
      ]
    }
  }
}

Tools listed

analyze-ai-vision-general, analyze-ai-vision-moderation, analyze-ai-vision-tagging, analyze-captioning, analyze-cld-fashion, analyze-cld-text, analyze-coco, analyze-google-logo-detection, analyze-google-tagging, analyze-human-anatomy, analyze-image-quality, analyze-lvis, analyze-shop-classifier, analyze-unidet, analyze-watermark-detection, tasks-get-status

Tool history: captured Nov 13, 2026. All tool history.

Quick config

{
  "mcpServers": {
    "cloudinary-analysis-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@cloudinary/analysis-mcp",
        "start"
      ]
    }
  }
}

Add to config Opens the config generator with this server selected.

Setup

  1. Install. Run npm install @cloudinary/analysis-mcp (Node 20). This is the exact command we ran on 2026-11-12.
  2. Configure. Add the mcpServers entry below to your MCP client config.
  3. Verify. Restart the client and check that tools/list returns tools (16 in our test).
{
  "mcpServers": {
    "cloudinary-analysis-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@cloudinary/analysis-mcp",
        "start"
      ]
    }
  }
}

Test history

Follow this server (RSS) · Monthly changelog

FAQ

Is Cloudinary Analysis MCP deprecated?

No. @cloudinary/analysis-mcp was not deprecated or archived when we last tested it on 2026-11-12.

What replaces Cloudinary Analysis MCP?

Nothing; Cloudinary Analysis MCP (official) is not deprecated as of 2026-11-12.

Does Cloudinary Analysis MCP need an API key?

It connects and lists 16 tools without a key, but every tool needs Cloudinary credentials or OAuth.

Embed the badge

TestedMCP: 70/100, tested 2026-11-12

Every tested server gets a free embeddable badge. It shows the current score and test date and expires after 90 days. Testing is free; payment never changes a score.

Claim this listing · Report an issue