webfetch

io.github.ashlraiPublished by GitHub account ashlraiv0.1.5Updated Nov 3, 2026

License-first federated image search with attribution, dimensions, and download tooling.

VerifiedSTDIODesktop onlyWeb Search & Scraping Media & Design

Server details

Identifier: io.github.ashlrai/webfetch
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account ashlrai for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.ashlrai%2Fwebfetch.svg)](https://sourceweft.com/mcp/io.github.ashlrai%2Fwebfetch?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Federated image search and download for agents, returning license tags, confidence scores and ready-to-use attribution lines.

What you can do: Search images across 25 providers with license policy, size filters and attribution
Search artist images by kind and canonical album covers
Download an image to a local cache with size cap, content-type guard and SHA-256 hash
Resolve the license of any URL and enumerate images on a page with heuristic licenses
Reverse-image-search a reference URL to find similar images
When to use it: Useful when an assistant needs to find reusable images for a page, deck or liner notes and must know whether each result is open, platform-licensed, editorial-only or exploration-only, with attribution text included.
Requirements: Runs locally via npm package getwebfetch-mcp over stdio; needs Node 18 or newer, or Bun 1.0 or newer. Basic use with Wikimedia Commons and Openverse needs no key. Optional keys: UNSPLASH_ACCESS_KEY, PEXELS_API_KEY, PIXABAY_API_KEY, BRAVE_API_KEY, SERPAPI_KEY (required for reverse image search); the README also lists Spotify and Bright Data variables. Network access required.

Before you install

Optional provider keys are secrets passed as environment variables. download_image writes files to a local cache directory. probe_page and fetch_with_license fetch third-party pages and images, and reverse-image-search results are leads that should be verified. The README's one-line installer downloads and runs a remote script and edits agent settings files; prefer manual configuration.

Installation

In SourceWeft

Open webfetch in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

webfetch MCP

License-first image search and download for any MCP-speaking agent.

Every result ships with a structured license tag (CC0, CC_BY, CC_BY_SA, platform-license tags, EDITORIAL_LICENSED, ...), a confidence score, and a ready-to-render attribution line. Covers 25 providers, with 19 in the default set — no API key needed for Wikimedia Commons, Openverse, iTunes, MusicBrainz CAA, NASA, The Met, Library of Congress, Internet Archive, Wellcome Collection, and Burst.

Why webfetch MCP?

Most image-search tools give you URLs. webfetch gives you URLs plus the legal metadata needed to classify them as open/commercial reusable, platform-license, editorial-only, or exploration-only. The MCP layer exposes seven composable tools — search, specialize by artist/album, download with a hash, resolve an arbitrary URL's license, reverse-image-search, and triage a source page — so an agent can go from prompt to attributed asset in a single conversation turn.

25 providers, 19 in the default set and many requiring no key at all
License-first ranking: CC0 floats to the top; heuristic-only results stay below 0.5 confidence
Attribution always included: one attributionLine string, ready for a tooltip or credits footer
Free tier needs no API key for Wikimedia and Openverse; full provider coverage adds optional keys per provider

Install

One-line (recommended)

Installs bun if missing, builds the server, symlinks webfetch onto $PATH, and merges the MCP block into ~/.claude/settings.json.

Claude Desktop / Claude Code

Add to ~/.claude/settings.json:

json

{  "mcpServers": {    "webfetch": {      "command": "bun",      "args": ["run", "/path/to/webfetch/packages/mcp/src/index.ts"]    }  }}

{  "mcpServers": {    "webfetch": {      "command": "bun",      "args": ["run", "/path/to/webfetch/packages/mcp/src/index.ts"]    }  }}

Cursor

Add to ~/.cursor/mcp.json:

json

{  "mcpServers": {    "webfetch": {      "command": "bun",      "args": ["run", "/path/to/webfetch/packages/mcp/src/index.ts"]    }  }}

{  "mcpServers": {    "webfetch": {      "command": "bun",      "args": ["run", "/path/to/webfetch/packages/mcp/src/index.ts"]    }  }}

Cline

Paste into Cline's MCP settings JSON (VSCode sidebar → Cline → MCP Servers):

json

{  "mcpServers": {    "webfetch": {      "command": "bun",      "args": ["run", "/path/to/webfetch/packages/mcp/src/index.ts"],      "disabled": false,      "autoApprove": ["search_images", "search_artist_images", "search_album_cover", "probe_page"]    }  }}

{  "mcpServers": {    "webfetch": {      "command": "bun",      "args": ["run", "/path/to/webfetch/packages/mcp/src/index.ts"],      "disabled": false,      "autoApprove": ["search_images", "search_artist_images", "search_album_cover", "probe_page"]    }  }}

Replace /path/to/webfetch with your clone path (default after installer: ~/.webfetch/repo).

Tools

Tool	Description	Key params
`search_images`	Federated search across 25 providers. Returns the top candidates with license + attribution. Does not download. For large batches, use CLI handoff: `webfetch batch --jsonl`.	`query`, `providers[]`, `licensePolicy`, `minWidth`, `minHeight`
`search_artist_images`	Specialized artist image search with kind-aware provider routing: `portrait`, `album`, `logo`, `performing`.	`artist`, `kind`, `providers[]`
`search_album_cover`	Canonical album artwork via MusicBrainz CAA + iTunes + Spotify. Results are `EDITORIAL_LICENSED`.	`artist`, `album`
`download_image`	Download a URL to local disk cache. 20 MB cap, content-type guard, SHA-256 hash, host blocklist enforced.	`url`, `maxBytes`, `cacheDir`
`fetch_with_license`	Resolve license for any URL via host heuristics + page metadata (`<link rel=license>`, `dc.rights`, OG tags).	`url`, `probe` (also download bytes)
`find_similar`	Reverse-image-search a reference URL. Requires `SERPAPI_KEY`. Returns leads — verify before shipping.	`url`, `providers[]`
`probe_page`	Enumerate every `<img>` on a webpage with inferred dimensions and per-image heuristic license. Respects `robots.txt`.	`url`, `respectRobots`

License tags

Results carry one of: CC0 · PUBLIC_DOMAIN · CC_BY · CC_BY_SA · UNSPLASH_LICENSE · PEXELS_LICENSE · PIXABAY_LICENSE · EDITORIAL_LICENSED · PRESS_KIT_ALLOWLIST · UNKNOWN (rejected by default). Use open-only when platform/editorial licenses are not acceptable.

Migration note: Unsplash, Pexels, and Pixabay are no longer reported as CC0. Agents should treat UNSPLASH_LICENSE, PEXELS_LICENSE, and PIXABAY_LICENSE as platform-license results, not Creative Commons/public domain results.

Batch handoff

MCP tools are meant for interactive agent calls. For hundreds or thousands of queries, have the agent hand off to the CLI:

Input lines are query or query<TAB>provider-a,provider-b. Each output line contains index, query, status, candidateCount, candidates, top, downloads, and provider diagnostics.

Auth / env vars

Provider	Env var	Free tier?
Wikimedia Commons	—	Yes (no key)
Openverse	—	Yes (no key)
Unsplash	`UNSPLASH_ACCESS_KEY`	Demo key rate-limited
Pexels	`PEXELS_API_KEY`	Free tier available
Pixabay	`PIXABAY_API_KEY`	Free tier available
Spotify	`SPOTIFY_CLIENT_ID` + `SPOTIFY_CLIENT_SECRET`	Dev app required
Brave Search	`BRAVE_API_KEY`	Free tier available
SerpApi	`SERPAPI_KEY`	Required for `find_similar`
Bright Data managed browser	`BRIGHTDATA_API_TOKEN`	Optional server/cloud fallback

MusicBrainz CAA and iTunes require no key. Missing keys cause the provider to skip gracefully — other providers still respond.

Demo prompts

Try these in Claude Code or Cursor after installing:

Probe the page at https://commons.wikimedia.org/wiki/File:Miles_Davis.jpg and tell me if I can use it commercially.

Probe the page at https://commons.wikimedia.org/wiki/File:Miles_Davis.jpg and tell me if I can use it commercially.

Requirements

Node ≥ 18 or Bun ≥ 1.0
No API key required for basic use (Wikimedia + Openverse cover most editorial needs)

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v0.1.5LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts

webfetch

Overview

Installation

In SourceWeft

Other MCP clients

README

webfetch MCP

Why webfetch MCP?

Install

One-line (recommended)

Claude Desktop / Claude Code

Cursor

Cline

Tools

License tags

Batch handoff

Auth / env vars

Demo prompts

Requirements

Links

Tools

Version history

Score