License-aware images for markdown: CC/stock search, screenshots, Mermaid diagrams, provenance
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
PIXABAY_API_KEYAPI keyoptionalOptional Pixabay API key (Openverse works without any key)
PEXELS_API_KEYAPI keyoptionalOptional Pexels API key (Openverse works without any key)
Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
search_imagesSearch Openverse (CC/PD), Pixabay and Pexels for images whose license passes the policy. Returns ranked candidates with normalized license info, risk level (people/logos) and a ready-made attribution line. Use short English queries (2-5 concrete nouns) for best results.Search Openverse (CC/PD), Pixabay and Pexels for images whose license passes the policy. Returns ranked candidates with normalized license info, risk level (people/logos) and a ready-made attribution line. Use short English queries (2-5 concrete nouns) for best results.
No input schema was published for this tool.
get_licenseReturn the normalized license, caveats, risk level and attribution text for an image id returned by search_images.Return the normalized license, caveats, risk level and attribution text for an image id returned by search_images.
No input schema was published for this tool.
analyze_documentParse a markdown file into blocks (headings, paragraphs, code, quotes, lists, existing images) with indices. Use this to decide where images belong, then call insert_image with after_block. Blocks of type code/quote/list/image are usually poor anchors.Parse a markdown file into blocks (headings, paragraphs, code, quotes, lists, existing images) with indices. Use this to decide where images belong, then call insert_image with after_block. Blocks of type code/quote/list/image are usually poor anchors.
No input schema was published for this tool.
insert_imageDownloads the image next to the document (images/ by default), inserts a markdown image + credit after the given block, and appends a provenance.json ledger entry recording the license as verified at insert time. Refuses to omit credit when the license requires attribution.Downloads the image next to the document (images/ by default), inserts a markdown image + credit after the given block, and appends a provenance.json ledger entry recording the license as verified at insert time. Refuses to omit credit when the license requires attribution.
No input schema was published for this tool.
replace_imageSwap an image previously inserted by insert_image (identified by its relative path in the markdown) for a new candidate id. Updates the file and the ledger.Swap an image previously inserted by insert_image (identified by its relative path in the markdown) for a new candidate id. Updates the file and the ledger.
No input schema was published for this tool.
list_ledgerList every image recorded in provenance.json for a document's images folder, with license and attribution as verified at insert time.List every image recorded in provenance.json for a document's images folder, with license and attribution as verified at insert time.
No input schema was published for this tool.
screenshot_urlCapture a URL (or a CSS-selected region) with a headless browser. Use ONLY when the text discusses that page/product/article — the capture is recorded with basis=quotation, not a license, and the credit shows source URL + capture date. Prefer selector/crop over full pages. If target_file is given t…Capture a URL (or a CSS-selected region) with a headless browser. Use ONLY when the text discusses that page/product/article — the capture is recorded with basis=quotation, not a license, and the credit shows source URL + capture date. Prefer selector/crop over full pages. If target_file is given t…
No input schema was published for this tool.
render_diagramTurn the article's own ideas into a diagram (flowchart, sequence, mindmap, timeline, pie, quadrant…) — best for structure/process/comparison paragraphs where a stock photo would be off-topic. Copyright-clean (basis=original). Give valid Mermaid code; Korean labels are fine. If target_file is given…Turn the article's own ideas into a diagram (flowchart, sequence, mindmap, timeline, pie, quadrant…) — best for structure/process/comparison paragraphs where a stock photo would be off-topic. Copyright-clean (basis=original). Give valid Mermaid code; Korean labels are fine. If target_file is given…
No input schema was published for this tool.
render_snippetFor remote clients that cannot write files: return markdown/HTML for an image candidate with the correct credit line, plus the direct image URL and a ledger-style provenance record the caller can store. Does not download anything.For remote clients that cannot write files: return markdown/HTML for an image candidate with the correct credit line, plus the direct image URL and a ledger-style provenance record the caller can store. Does not download anything.
No input schema was published for this tool.
9 of 9 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
License-aware images for markdown: CC/stock search, screenshots, Mermaid diagrams, provenance
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the 60-package limit. The rest of the tree was never resolved.
36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)
133 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+121 more not listed. The counts by reason above cover all of them.
Not followed: peerDependencies, optionalDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.