mcp server
Intelligence Aeternum
AI training dataset marketplace: 2M+ museum artworks with Golden Codex enrichment
Description as published by the maintainer. Source
- version 1.0.0
- slowing
slowing — Most recent push to the repository was 2026-02-25.
What this server can do
13 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
deliver_artifacts(tier, format, artifact_ids)- Create an on-demand delivery order for specific manifest artifacts. Artifacts are fetched from museum APIs, optimized, enriched (Nova + Atlas), and bundled into a single downloadable archive. Supports up to 10,000 artifacts per order with automatic volume discounts. Args: artifact_ids: Comma-separated artifact IDs (e.g., "met_436965,chicago_27992"). Up to 10,000 per order. tier: Delivery tier: human_standard ($0.05) or hybrid_premium ($0.20). format: Output format: 'tar.gz' (default, best for ML pipelines), 'zip' (best for humans), or 'urls' (legacy individual signed URLs). Required: artifact_ids.
enrich_agent_image(tier, image_url, callback_url, custom_fields)- Submit YOUR image for Golden Codex enrichment (Enrichment-as-a-Service). Tiers: - oracle_only: Returns Golden Codex JSON (111-field Hybrid_Premium analysis) - oracle_plus_infuse: JSON + XMP-infused image + GCX hash registry - full_certified: JSON + infused + C2PA signed + hash registered Custom fields are merged with Hybrid_Premium analysis. Submit as JSON string. Your values take priority for factual fields (title, artist, copyright). Args: image_url: Public URL of the image to enrich. tier: oracle_only, oracle_plus_infuse, or full_certified. callback_url: Optional webhook URL for completion notification. custom_fields: JSON string of custom metadata fields to merge. Required: image_url.
get_agent_guide- FREE — Get complete API workflow documentation for agents. Returns the full agent guide with endpoints, pricing, custom fields schema, volume discounts, and recommended workflow.
get_compliance_manifest(dataset_id, regulation)- FREE — Get auto-generated regulatory compliance manifests for a dataset. Returns AB 2013 (California) and/or EU AI Act Article 53 provenance manifests. "Buy from us, get instant California + EU AI compliance." Args: dataset_id: The dataset ID (e.g., "met-museum", "rijksmuseum"). regulation: Which regulation: "ab2013", "eu_ai_act", or "all" (default). Required: dataset_id.
get_curated_metadata(artifact_id)- FREE (5/day) — Get Human_Standard metadata + image for an artifact. Returns 500-1,200 tokens of 100% human-sourced metadata PLUS a signed image download URL. Every response is a package: metadata + image together. Zero synthetic content. Sources: Museum API + Wikipedia + Wikidata + Getty ULAN. After 5 free requests per day, requires $0.05 USDC via x402. Args: artifact_id: The artifact ID (e.g., "met_10049", "nga_1234"). Required: artifact_id.
get_enrichment_status(job_id)- Poll the status of a Golden Codex enrichment job. Args: job_id: The job ID returned from the enrich endpoint. Required: job_id.
get_oracle_metadata(artifact_id)- PAID — Get Hybrid_Premium metadata + image with VLM deep visual analysis. Returns 2,000-6,000 tokens including everything in Human_Standard PLUS: visual_analysis, emotional_and_thematic_journey, deep symbolism, and archetypal analysis. Image download URL included in response. Args: artifact_id: The artifact ID (e.g., "met_10049"). Required: artifact_id.
get_pricing(quantity, dataset_id)- FREE — Get pricing information for a dataset purchase. Args: dataset_id: The dataset ID. quantity: Number of images to price. Required: dataset_id.
list_enrichment_tiers- FREE — List available enrichment tiers for agent-submitted images. NEW: Submit YOUR images via POST /agent/enrich with custom fields. Your metadata is merged with Oracle analysis. Submitter values take priority.
preview_dataset(limit, dataset_id)- FREE (10/day) — Preview sample images from a dataset. Required: dataset_id.
purchase_dataset(quantity, dataset_id, payment_method)- Initiate a dataset purchase (x402 or Stripe). Required: dataset_id, quantity.
search_alexandria(limit, query, museum)- FREE — Search 2M+ museum artworks in the Alexandria Aeternum catalog. Searches the Firestore manifest (primary) with Vertex AI fallback. Returns artifact IDs, titles, artists, dates, and classification. Use get_curated_metadata() for Human_Standard metadata + image (5 free/day). Use get_oracle_metadata() for Hybrid_Premium VLM deep analysis + image. Args: query: Free-text search (e.g., "impressionist landscape", "Rembrandt portrait"). museum: Filter by museum: met, nga, chicago, cleveland, rijksmuseum, smithsonian, paris. limit: Max results (default 20, max 100). Required: query.
search_datasets(query, domain, min_images)- FREE — Search the Alexandria Aeternum dataset catalog (7 museums, 1.6M+ images).
Last successful function declaration observed on . Source: https://data-portal-172867820131.us-west1.run.app/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://data-portal-172867820131.us-west1.run.app/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 1 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-02-25 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 1 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Latest published version | 1.0.0 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-02-25 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| First listed in the MCP Registry | 2026-02-25 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub | |
| mcp tools declared | 13 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | data-portal-172867820131.us-west1.run.app | |
| mcp endpoint status | ok | The server listed 13 functions when asked. | as of probe | data-portal-172867820131.us-west1.run.app |
Where to get it
Related, by what their authors tagged them
-
io.github.codex-curator/studiomcphub
— last commit 2026-05-14, shares golden-codex, provenance, x402
32 creative AI tools (18 free) for agents: generate, upscale, mockup, print, watermark.
-
io.github.amitsingh-24/pixlint
— last commit 2026-07-27, shares datasets
Lint, curate & prepare computer-vision datasets from your AI assistant — MCP server, 67 tools
-
Macfax
— last commit 2026-07-20, shares marketplace
Used-Mac market: quality-gated listings with deep links, asking-price stats, trust checks, alerts.
-
io.github.archimedes-market/mcp-archimedes
— last commit 2026-07-12, shares marketplace
Discover verified deep-tech engineering bounties from any AI agent.
-
io.github.Avivcha/pody-mcp
— last commit 2026-06-20, shares marketplace
Israeli podcast & content marketplace MCP — 7 tools: studios, podcasts, glossary, industry report.
-
Bankstatemently
— last commit 2026-08-06, shares marketplace
Parse PDF bank statements into structured transactions, accounts, and balances.
-
io.github.elchin92/avito-mcp
— last commit 2026-08-03, shares marketplace
An AI agent that runs your Avito account — 148 tools for chats, listings, promotion, orders.
-
elisym
— last commit 2026-07-30, shares marketplace
AI agent discovery, marketplace, messaging, and payments on Nostr - no platform, no middleman
-
Fabric Marketplace
— last commit 2026-04-28, shares marketplace
Agent-native marketplace. Bootstrap, list inventory, search, negotiate, and trade via MCP.
-
dev.tatastu/proof
— last commit 2026-07-19, shares provenance
Stamp content with permanent, verifiable provenance. Hash locally, verify free forever.
These share tags the maintainers applied themselves, such as golden-codex, provenance, x402, datasets. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.
This is not a recommendation and not a test result. It is a map of what the authors said their work is about.
How the author describes it
Topics the maintainer set on GitHub: ai, ai-training-data, datasets, golden-codex, marketplace, mcp, mcp-server, museum-art, provenance, x402.
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json