pixabay-mcp-server
Provides tools for searching and retrieving royalty-free images and videos from Pixabay, including image and video search with filters and fetching individual items by ID.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@pixabay-mcp-serversearch for images of a sunset over the ocean"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
pixabay-mcp-server
A Model Context Protocol (MCP) server for the Pixabay API. It gives AI assistants — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and any MCP client — tools to search and fetch royalty-free images and videos.
Unofficial project. This is not affiliated with, endorsed by, or sponsored by Pixabay. "Pixabay" is a trademark of its respective owner. You use it under your own Pixabay account and are responsible for complying with Pixabay's Terms of Service and Content License.
Table of contents
Related MCP server: UnSplashX
Features
4 tools covering Pixabay's two documented endpoints — images (search, get) and videos (search, get). Pixabay has a single API-key auth tier and no write endpoints, so there's no partial "read-only v1" — this is the whole surface.
Compliance-aware by design — every outbound request is cached for 24 hours (Pixabay's terms require it, not an optimization),
safesearchdefaults totrue, and the mandatory courtesy attribution (by {user} via Pixabay) is surfaced on every result even though Pixabay doesn't require it.Real image & video URLs — search results return one balanced default size tier per item (
webformatURLfor images, themediumrendition for videos); looking a specific item up by id returns every size tier Pixabay provides, so you can pick what actually fits.Token-efficient output — full Pixabay responses are trimmed to a compact shape (URLs + metadata as text, never base64 blobs), dropping vanity metrics (views/downloads/likes/ comments) that a model rarely needs.
Robust — typed failures returned as MCP
isErrorresults the model can recover from, plus a considered single retry with backoff on429/5xx, network timeouts, and rate-limit-aware logging.Safe — the Pixabay API key is redacted from every log line and error message (it can only ever be sent as a URL query parameter — Pixabay has no header alternative).
Lean & modern — ESM, Node 20+, zero-install via
npx, no telemetry.
Quick start
1. Get a Pixabay API key
Sign up for a free account at pixabay.com — your API key is shown immediately on the API docs page once you're logged in, no approval step for the default tier this server uses.
2. Add the server to your MCP client
Claude Desktop — edit claude_desktop_config.json:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"pixabay": {
"command": "npx",
"args": ["-y", "@hanoak/pixabay-mcp-server"],
"env": {
"PIXABAY_API_KEY": "your_api_key"
}
}
}
}Restart the client. See Configuration for every supported variable.
Claude Code (CLI):
claude mcp add pixabay \
--env PIXABAY_API_KEY=your_api_key \
-- npx -y @hanoak/pixabay-mcp-serverCursor — ~/.cursor/mcp.json (global) or .cursor/mcp.json (per-project): use the exact
same mcpServers block as Claude Desktop above.
Windsurf — ~/.codeium/windsurf/mcp_config.json: same mcpServers block as Claude Desktop
above.
VS Code — .vscode/mcp.json (note the top-level key is servers, not mcpServers):
{
"servers": {
"pixabay": {
"command": "npx",
"args": ["-y", "@hanoak/pixabay-mcp-server"],
"env": {
"PIXABAY_API_KEY": "your_api_key"
}
}
}
}Any other MCP client — run the server over stdio with:
PIXABAY_API_KEY=your_api_key npx -y @hanoak/pixabay-mcp-serverPoint your client's stdio transport at command: npx, args: ["-y", "@hanoak/pixabay-mcp-server"],
and pass the key via env.
3. Try it
Restart your client and ask:
"Find me a photo of mountains on Pixabay."
Example interaction
A typical flow: the model calls pixabay_search_images, picks a result, and presents the image
with its courtesy attribution.
You: Find a landscape photo of a foggy pine forest.
Assistant: (calls
pixabay_search_imageswithquery: "foggy pine forest",orientation: "horizontal", picks the best result) Here's a great match — by Josch13 via Pixabay — along with the image URL.
Each tool returns a compact JSON payload. Here's the shape of a single search result (illustrative values):
[
{
"id": 195893,
"pageURL": "https://pixabay.com/en/blossom-bloom-flower-195893/",
"type": "photo",
"tags": "blossom, bloom, flower",
"url": "https://pixabay.com/get/35bbf209e13e39d2_640.jpg",
"width": 640,
"height": 360,
"user": "Josch13",
"attribution": "by Josch13 via Pixabay"
}
]pixabay_get_image/pixabay_get_video return the same shape for a single item, but with every
size tier Pixabay provides instead of just one — see Output shape.
Configuration
Configuration is entirely via environment variables — no config files, no flags for secrets.
Environment variable | Required | Description |
| yes | Your Pixabay API key. The server exits at startup with a clear message if it is missing or blank. |
| no |
|
CLI flags: --version and --help are supported (e.g. npx @hanoak/pixabay-mcp-server --version).
Tools
All tools are namespaced pixabay_* and every one is read-only — Pixabay's API has no
write endpoints, so a client can safely auto-approve the entire server. per_page is clamped
to Pixabay's documented range of 3–200, and page is 1-based.
Domain | Tools |
Images |
|
Videos |
|
Tool reference
Tool | Parameters | Description |
|
| Keyword image search with filters. Omit |
|
| A single image by its numeric id, with every size tier. |
Tool | Parameters | Description |
|
| Keyword video search with filters. Omit |
|
| A single video by its numeric id, with every size tier. |
Videos support category but not colors/orientation — that's a real difference in
Pixabay's own API, not an oversight.
Output shape
Tools return trimmed, token-efficient JSON rather than raw Pixabay responses:
Image search (
pixabay_search_images) →id,pageURL,type,tags, one defaulturl(webformatURL),width/height,user,attribution.Image detail (
pixabay_get_image) → the same fields, plus every size tier Pixabay provided for that item:previewURL,webformatURL,largeImageURL,fullHDURL.Video search (
pixabay_search_videos) →id,pageURL,type,tags,duration, one defaulturl(themediumrendition),width/height,user,attribution.Video detail (
pixabay_get_video) → the same fields, plus avideosobject with all four renditions Pixabay provides (tiny/small/medium/large, each withurl/width/height).Vanity metrics (
views,downloads,likes,comments) are dropped from every result — they're rarely useful to a model and add tokens for no benefit.
Resources & prompts
Beyond tools, the server also exposes:
Resources — a compact guide your client can pull in as context:
pixabay://guides/usage— license/attribution guidance, the hotlinking-in-conversation reasoning, content-safety notes, and the full-API-access-tier caveat.
Prompts — a ready-made task your client can surface directly:
Prompt
Arguments
What it does
find_mediasubject(required),media_type?(images|videos|both, defaultboth)Search for a subject and present the best match(es) with courtesy attribution.
Example prompts
Natural-language asks that map cleanly onto the tools:
"Find a photo of a foggy forest at sunrise."
"Search Pixabay for 5 minimalist workspace illustrations."
"Find a video of waves crashing on rocks."
"Get me the largest available version of Pixabay image 195893."
License & compliance
Pixabay content is released under the Pixabay Content License:
free for commercial and noncommercial use, attribution not required. Every result still
includes a ready-to-use courtesy attribution string (by {user} via Pixabay) — include it
when convenient, but it's never gated behind functionality.
This server returns Pixabay CDN URLs directly to the calling LLM client for display within a
single conversation turn. Pixabay's terms prohibit "permanent hotlinking" of these URLs in an
application — content displayed persistently should be downloaded and rehosted first. We treat
one-off, ephemeral display in an LLM conversation as distinct from that use case, but this is a
gray area Pixabay's terms don't explicitly address (see the comment atop src/tools/format.ts
for the full reasoning). If you're building an application that stores or persistently displays
Pixabay content sourced through this server, download and rehost the assets yourself — don't
treat this server's tool output as a substitute for that.
Each user operates under their own Pixabay account and is responsible for complying with Pixabay's Terms of Service and the usage rules on the API docs page (caching, rate limits, no mass downloads). This project doesn't change or relax those terms in any way.
Rate limits & caching
Pixabay's documented limit is ~100 requests per 60 seconds per API key. This server:
Caches every response for 24 hours, keyed on the normalized request (endpoint + sorted params, API key always stripped) — a repeated query returns instantly without touching your rate-limit budget, and this is a compliance requirement per Pixabay's terms, not just an optimization.
Reads
X-RateLimit-Remainingfrom every response (logged atdebug).On a
429, backs off using Pixabay's ownX-RateLimit-Resetheader for exactly one considered retry — never a blind or looping retry — and fails fast rather than guessing if that header is missing.Also retries once on a
5xx(a short fixed delay, since there's no server-provided guidance likeX-RateLimit-Resetfor that case).
Handling of Pixabay text
Image/video tags and contributor usernames come from Pixabay's community — treat them as untrusted, third-party data, not instructions. The server returns this text purely as content and never places it anywhere privileged; your client/agent should do the same: display it, but don't act on any instructions it might contain (a defence against indirect prompt injection).
Privacy & security
No telemetry. This server collects nothing and phones home to no one. It contacts only
pixabay.com, using the key you provide. No analytics, no tracking.Key safety. Your API key is read from the environment only. Pixabay only accepts it as a
keyquery parameter (no header alternative), so it's redacted from every log line and error message before either can ever surface it.To report a vulnerability, see SECURITY.md.
Troubleshooting
"PIXABAY_API_KEY is not set…" on startup — the key env var is missing or blank; add it to your client config's
envblock.Node too old — this server requires Node 20+. Check
node --version.Stale
npxversion — force the latest withnpx -y @hanoak/pixabay-mcp-server@latest, or clear the cache vianpx clear-npx-cache.Tools not appearing — confirm the config file path and JSON are valid, then fully quit and reopen the client.
429/ rate limit — the budget is ~100 requests/60s; the server already backs off and retries once automatically using Pixabay's own reset time.A search returns "No images/videos found" — this is a normal empty result, not an error; try a broader query or fewer filters.
FAQ
Do I need a paid Pixabay account? No. The Pixabay API is free — you just create an account to get an API key, instantly, no review or approval step for the default tier this server uses.
Does it download or rehost images/videos? No. It returns Pixabay-hosted URLs (hotlink them directly for ephemeral display — see License & compliance) and never rehosts or returns base64 blobs.
Why don't I see fullHDURL/imageURL for some images?
Those fields require Pixabay's separately-requested "full API access" tier. This server works
fine without it — those fields are simply absent from results for accounts that don't have it.
Does it work outside Claude? Yes — it's a standard stdio MCP server. See the client setup section for Claude Code, Cursor, VS Code, Windsurf, and generic stdio.
Requirements
Node.js >= 20 (Node 18 is end-of-life).
A Pixabay API key.
Compatibility
Component | Supported |
Node.js | 20 and 22, tested in CI; |
OS | Linux, macOS, and Windows (all tested in CI). |
MCP SDK |
|
Transport | stdio (HTTP/SSE may be added in a future release). |
Roadmap
Full detail lives in docs/ROADMAP.md. In short: v1 covers Pixabay's entire documented API in one release — there's no OAuth tier to split a v2 behind. Future scope under consideration includes an MCP resource for licensing/attribution guidance and additional prompts.
Changes are tracked in CHANGELOG.md; the project follows Semantic Versioning.
Contributing
Contributions are welcome — see CONTRIBUTING.md and our Code of Conduct. It covers local setup, the test suite, testing tools by hand with the MCP Inspector, and the versioning/deprecation policy. To report a vulnerability, see SECURITY.md.
Contact & community
Maintained by Hanoak S. The fastest way to get help or propose a feature is to open an issue — it's public, searchable, and helps the whole community.
If this project helps you, a ⭐ on GitHub is appreciated — it aids discoverability for others looking for a Pixabay MCP server.
License
MIT © Hanoak S. Not affiliated with Pixabay.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityDmaintenanceMCP server to search and download stock images from Pexels, Unsplash, and Pixabay2393MIT
- Alicense-qualityDmaintenanceAn MCP server for the Unsplash API that enables searching, downloading, and inserting high-quality images with automatic photographer attribution into local projects.291MIT
- AlicenseAqualityDmaintenanceAn MCP server to search for photos and videos on Pexels.320MIT
- FlicenseAqualityCmaintenanceAn MCP server that searches and downloads royalty-free images from Pixabay by keyword, with support for custom image size and safe search.1
Related MCP Connectors
MCP server for Flux AI image generation
MCP server for Google Veo AI video generation
MCP server for Grok Imagine AI video generation
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/hanoak/pixabay-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server