Provenio
About
Art provenance intelligence: 282,731-node knowledge graph over Getty Provenance Index, Knoedler stock books, and wartime-restitution records — every answer cited, custody gaps named. Free keyless remote: https://provenio.art/api/mcp
Details
- Transport
- SSE
Explore
Setup
Install Provenio in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/mildo-ai/provenio
Follow the installation instructions in the repository README, then restart your MCP client.
search_artists
Cost: ~0.4s. Shortlist person nodes by name/nationality/era. Returns [{id, display_name, birth_year, death_year, nationality, era}]. Use when: you have a name but no person ID. Try a partial name if exact match fails (e.g. 'Basquiat' not 'Jean-Michel Basquiat'). Do NOT use if: you already know the ID — call get_artist directly (one call). Returns person IDs in 'person:slug' format — pass these directly as the 'artist' parameter in search_artworks. STOP after this unless you need a specific ar…
search_artworks
Cost: ~0.5s. Shortlist artworks by title/artist/medium/date, or risk-filter (provenance_risk, attribution_status). Returns summary rows. Use when: you need a list, not one work's detail. Do NOT use if: you know the artwork ID — call get_artwork (one call contains iconography + custody + polity + transactions). Do NOT chain multiple search_artworks calls for the same work — use get_artwork after you have the ID. Do NOT put artist names in the query field alone — use the artist filter with the …
search_auction_history
Cost: ~0.7s. Auction transaction rows with optional percentile_summary=true to also return P25/50/75/90 + realized-vs-estimate in ONE call. Use when: need lot-level prices OR percentile stats. Do NOT use if: you only need per-artist aggregates — use query_market_summary. SINGLE-CALL FRIENDLY — combine filters + percentile_summary for appraisal work.
get_artist
Cost: ~1s. Composite artist profile — identity + reception + 1-hop influence in/out + education + market aggregates. SINGLE CALL USUALLY SUFFICIENT. Use when: you have an artist ID and need their full picture. Do NOT chain with get_influence_network unless you need depth > 1. Do NOT use for multi-artist comparison — use query_market_summary.
get_artwork
Cost: ~1s. Composite artwork profile — metadata + Panofsky subjects + reception + custody + polity + transactions. SINGLE CALL USUALLY SUFFICIENT. Use when: you have an artwork ID. Do NOT chain with get_provenance_chain unless you need gap-risk flags specifically.
get_movement_context
Cost: ~0.5s. Concept node + linked artworks. Pass cross_tradition=true for hasFunctionalAnalog concepts (lotus↔rose). SINGLE CALL USUALLY SUFFICIENT. Use when: definitional context or iconography cluster. Do NOT use for artwork filters — use search_artworks.
get_influence_network
Cost: ~2-3s. N-hop influence BFS. Use ONLY when depth>1 needed — get_artist already has 1-hop.
get_reception_arc
Cost: ~1s. Time-ordered reception claims for artist or artwork. Use for valence-shift narrative. Use query_reception_price_correlation if you also need price.
get_provenance_chain
Cost: ~1s. Custody timeline + gap-risk flags (Nazi, colonial, Russian Rev, Knoedler 1970-2009). Use only for deep due diligence — get_artwork already has basic custody.
get_lineage_cluster
Cost: ~1s. Formal teacher/student cluster (education_lineage). Use for academic lineage. For conceptual influence: get_influence_network.
find_comparable_artworks
Cost: ~2s. Comparable set. EITHER artwork_id seed → similar works, OR artist_id seed → peer artists. Not for same-artist lot history (use search_auction_history).
query_market_summary
Cost: ~2s. Per-artist market aggregates × reception × polity. Use for cross-artist comparison. Single artist deep profile: get_artist. Individual lots: search_auction_history.
query_polity_dispersal
Cost: ~2s. Polity-origin artworks now dispersed. Use for restitution/cultural-heritage analysis. For simple list: search_artworks.
get_exhibition_history
Cost: ~0.5s–1s. Exhibition history for an artist OR artwork. SINGLE CALL. Returns normalised exhibition records (exhibitions table) when available; falls back to knowledge-graph event nodes (raw_json scan) when the normalised table is empty. Coverage: 94 curated events for 20+ artists as of 2026-04-24. For artists with no data, returns actionable guidance including the exact CLI command to run artsy_exhibitions.py to ingest missing records. Always returns coverage_gaps and suggested_next_tool…
get_career_trajectory
Cost: ~2s. Artist career trajectory analysis: milestones, career stage, pattern detection (A–E), and comparable historical artists who followed the same path. Career stages: PRE_MARKET → REGIONAL → CRITICAL_PHASE → MARKET_ENTRY → ESTABLISHED. Patterns: A=institutional escalation, B=curator championing, C=movement anchor, D=late market discovery, E=diaspora rediscovery. Use for: emerging artist discovery, gallery acquisition decisions, curator narrative building. Do NOT use for purely biograph…
query_reception_price_correlation
Cost: ~2s. Reception × price timeline for one artist. Combines get_reception_arc + price trend in one call.
compare_career_patterns
Cost: ~4s. Side-by-side career trajectory comparison for two artists. Returns full trajectory data for each + a structured comparison: pattern overlap score, career stage delta, exhibition/market delta, interpretation, and recommendation. Use when: gallery wants to pitch an emerging artist by showing they mirror a validated comparable's early career. Use when: curator needs narrative evidence that artist A is at the same inflection point artist B was at in year X. Do NOT use when: you need da…
find_emerging_artists_by_pattern
Cost: ~3s. Discover emerging artists whose current KG footprint matches a historical career pattern. Patterns: A=institutional_escalation, B=curator_championing, C=movement_anchor, D=late_market_discovery, E=diaspora_rediscovery. Returns ranked candidates with confidence score, exhibition/market data, and signal summary. Use when: gallery wants a shortlist of artists at an early inflection point matching a proven pattern. Use when: curator is building a thematic exhibition and wants artists a…
search_galleries
Cost: ~1s. Search galleries by name, tier, country, or city. Tiers: mega (Gagosian/Zwirner level), major (international program), boutique (focused), emerging (newer). Use when: identifying which galleries operate in a specific market or tier band. Use when: building a B2B target list (galleries by region/tier). Do NOT use when: you want to know which gallery represents a specific artist — use find_galleries_by_artist instead.
get_gallery_artists
Cost: ~1s. Get the represented-artist roster for a specific gallery. Returns: gallery metadata + ordered list of artists with exclusivity (exclusive/shared/former/deceased_estate), period, notes. Use when: preparing pitch context for a specific gallery (cold email, fair planning). Use when: validating whether artist representation overlap exists between two galleries. Do NOT use when: you only have the artist name — use find_galleries_by_artist instead.
find_galleries_by_artist
Cost: ~1s. Find all galleries that represent (currently or formerly) a specific artist. Returns: ordered list of representations (current first, then deceased_estate, then former), with gallery tier/city/country and period. Use when: verifying primary-market representation for valuation or attribution context. Use when: building artist-centric outreach (which galleries control supply). Use when: tracking representation history for a deceased artist's estate.
lookup_met_museum
Cost: ~0.3s. Search the Metropolitan Museum of Art collection (free public API · ~480K objects) and optionally dereference an objectID. Use when: you need a museum-confirmed match for an artist or work, or want to triangulate Provenio data against Met holdings. Returns either {total, objectIDs[]} for a search OR a full object record if object_id supplied. Source: https://collectionapi.metmuseum.org/public/collection/v1 · zero PII, public domain images flagged.
lookup_europeana
Cost: ~0.5s. Search the Europeana cultural heritage corpus (~50M records from EU museums/archives) for art records. Use when: triangulating Provenio data against European museum holdings, or finding object records with images for a Western European artist. Returns: {total, items: [{title, creator, dataProvider, year, image_url, edm_url}]} Source: api.europeana.eu (public-domain Europe gateway, demo key embedded; users can supply own key via byok_external_query for high-volume).
lookup_wikidata_art
Cost: ~3-8s. Run a SPARQL query against Wikidata (public, no auth) for art-related entities. Use when: you need cross-museum location data for an artist's works, or biographical data not in Provenio. Pattern: pass a SPARQL query string. Example below to get all Klimt artworks with current location. Returns: {total, bindings: [...]} — raw SPARQL JSON results format. Source: https://query.wikidata.org/sparql · 12-second SPARQL query timeout enforced.
byok_external_query
Cost: ~variable. Forward a JSON HTTP request to YOUR own external API endpoint and return the response. Use when: you need to query a third-party art-market source (Artnet/Artprice/your own gallery DB) that we do not host. Auth: pass your API key in MCP request header 'x-byok-auth' — we forward it as Authorization to your endpoint. Allowed hosts: must match an HTTPS URL on the public internet (no internal IPs, localhost, file://, etc). Returns: {status, body, headers, fetched_at, source_url} …
Provenance and market intelligence for AI agents.A 282,731-node knowledge graph over 273,378 art-market transactions — the Getty Provenance Index, the Knoedler stock books (1872–1971), ERR and wartime-restitution records — served to any MCP-compliant client.
Every answer is cited. Custody gaps are named, never guessed.Hallucination is held under 1%, verified by an externally reproducible evaluation harness rather than self-report. Where the record is silent, Provenio returns an explicit gap — it never asserts clean title.
🌐https://provenio.art· Free open beta — no key, no card.
Add the remote server to any MCP client:
- Claude(claude.ai / Desktop): Settings → Connectors → Add custom connector → paste the URL
- ChatGPT(MCP enabled): add as a connector —search/fetchcompatible
- Cursor / other clients: streamable-http transport, no auth header needed
Open beta: 5,000 queries/month per IP, all 27 tools, full corpus. Need a higher cap? Write to[email protected].
- get_provenance_chain— full custody chain with verification state and risk-window flags; always returnschecked_databases
- search_auction_history— lot-level prices with optional P25/50/75/90 percentile summary in one call
- find_comparable_artworks— era-precise, market-guarded comparables
- get_influence_network/get_reception_arc— scholarly influence and verbatim critical reception with source refs
- byok_external_query— federate your own Artnet/Artprice/gallery-DB credentials (SSRF-guarded)
Full catalogue:provenio.art/docs·OpenAPI 3.1 spec
- Official MCP Registry:io.github.mildo-ai/provenio
- Smithery:mildo-ai/provenio
Provenio's design contract, in one line:no model memorises art history — Provenio lets any model cite it.Every response binds to a verifiable source row; absences come back as namedcoverage_gaps; the evaluation harness that certifies the <1% hallucination rate is re-runnable against the live API.
Read the methodology:The Invisible Gaps·Genesis — the artwork
Found a wrong price, a broken custody chain, a missing attribution — or want a tool that doesn't exist yet?Open an issue. Data corrections are applied only with a citable source, and every applied correction is noted in the release log. You can also write to[email protected].
Built and operated byHoyeob Kim· Mildo Inc. · Contact:[email protected]
This repository hosts the public server manifest and documentation for the hosted MCP service. The knowledge-graph pipeline and web application live in a private monorepo.
Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.
Persistent shared memory for AI agents. Hybrid search (pgvector + tsvector), knowledge graph, cognitive scoring - 97.2% Recall@10 on LongMemEval
Persistent coding memory for AI assistants — MCP stdio + remote URL, hybrid search, knowledge graph, token-efficient context. Self-host on Cloudflare D1 or Postgres.
Search concept relationships in the Unreal Engine official documentation using a Neo4j-powered knowledge graph.
Neo4j graph database server (schema + read/write-cypher) and separate graph database backed memory
Remote MCP for commodities research — knowledge graph, COT positioning, natural gas storage/weather, futures quotes, and private stories/journals. Requires Arc Research Starter + bearer token.
A task management system for LLM agents to manage projects, tasks, and knowledge using a Neo4j database for complex workflow automation.
MCP server for live NFL and fantasy football data, powered by gamedai Scout: player grades, start/sit calls, and a grounded football knowledge graph.
Mines git history for file co-change patterns into a queryable knowledge graph via MCP.
Query a hybrid graph (Neo4j) and vector (Qdrant) database for powerful semantic and graph-based document retrieval.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
