MemeStack MCP

Search the MemeStack image gallery. Runs semantic AI and keyword matching in parallel and merges results. Returns images with captions, tags, zap stats, and URLs.

Get full metadata for a specific image by ID, including caption, alt text, tags, OCR text, zap stats, and URLs.

Find visually similar images using perceptual hash matching. Returns images that look alike.

Find semantically related images using AI embedding similarity. Returns images with similar meaning/topic.

Browse and filter the image gallery without a search query. Useful for discovering content by tag, trending, or recent uploads.

Get a user's public profile including display name, stats, and avatar info.

Get top-ranked images by zaps received, or top zappers by amount zapped, over a time period.

Browse images for a specific tag. Returns the tag profile (description, stats) and optionally a paginated list of images tagged with it.

Get a category and its featured images. Categories group related tags (e.g. "charts", "memes", "lightning-network").

List all available image categories. Use this to discover what categories exist before calling browse_by_category.

Get the profile for a tag (description, image count, total zaps, related tags) without fetching any images. Use browse_by_tag to also retrieve images.

Get all variants of a meme template tracked on MemeStack. Returns the dominant image plus every variant in the same mutation group, with citation blocks for each. Use this to research how a meme has evolved or to find variants of a known image.

Search for images by the text written or printed in them (OCR). Different from regular search — only matches the text_in_image field, not captions or tags. Use this to find screenshots of specific quotes, signs, watermarks, or memes with specific embedded text.

Find a meme that captures a vibe, idea, or concept. Returns ready-to-embed images with citation blocks. Use this when writing posts, articles, or social content and you need a meme to illustrate a point.

List the most-used tags on MemeStack by all-time usage count. (Time-period filtering is not yet supported — tag usage is currently counted across the full lifetime of each tag.)

Suggest tag slugs matching a prefix. Use this to verify a tag exists before filtering by it, or to discover related tags. Prefix must be ≥ 2 characters.

Generate canonical attribution blocks for one or more MemeStack images. Returns markdown, HTML, and plain-text citation strings ready to paste into your output, plus a combined block for citing multiple images at once.

Find MemeStack images that look visually similar to a given image. Accepts an HTTPS image URL or a `data:image/...;base64,...` URL for bytes pasted into agent context. Returns visually-similar matches via perceptual-hash (dHash) hamming distance, with citation blocks. Heavily rate-limited (10/min/IP) since each call hashes the input.

Submit an image to the MemeStack review queue. Paid tool — 100 sats (or USDC equivalent) per submission via the agent payment rails (x402/L402); no account or API key. IMPORTANT: there is NO refund if moderation rejects the submission (duplicate, nsfw/spam, low quality) — the fee is the anti-spam mechanism. Accepted images await human review before publication. Accepts an HTTPS image URL or a data:image/...;base64 URL (JPEG/PNG/WebP, max 8MB). Optional caption/tags/attribution are hints shown to the AI tagger and moderators — never published verbatim. If the call fails or times out, retry with the SAME payment proof to resume — one payment delivers at most one submission and is never charged twice (up to 10 delivery attempts per payment; a corrected image_url is allowed while no submission has been created yet). Note for x402 clients: 100 sats exceeds the agents-SDK default per-call cap of $0.10 whenever BTC trades above $100k — raise maxPaymentValue in withX402Client if payment is refused client-side.

Generate a new image from a text prompt using AI (Grok Imagine). Paid tool — billed per call via the agent payment rails (x402/L402); not covered by any free quota. Generation runs asynchronously on the server and this call polls until it completes, up to ~90 seconds. If you get a "still running" error, call the tool again with the SAME payment proof to resume polling — you will never be charged twice for one payment. Note for x402 clients: "quality" mode (~$0.15) exceeds the agents-SDK default per-call cap of $0.10 — raise maxPaymentValue in withX402Client to use it.