Skip to main content
Glama

GAIP Digital Art Intelligence Agent

by io.github.tjcgraham-rgb
OverviewDiscussionsAdmin

Server Details

No longer listed separately (still callable): public provenance evidence for art collections.

Ownership verified
Status
Healthy
Uptime
100.0% over 22 days
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
tjcgraham-rgb/gaip-agents
GitHub Stars
0
Server Listing
gaip-broker

TDQS

A4.5/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool is exposed, so there is no risk of misselection or overlap with another tool. Its purpose—checking agreement among public NFT/digital-art records—is clearly distinct.

Naming Consistency5/5

The single tool name evaluate_public_art_evidence follows a clear verb_noun pattern in snake_case. With no other tools, there is no inconsistency to assess.

Tool Count3/5

A single tool is borderline thin for a server framed as a 'Digital Art Intelligence Agent,' though the tool itself is self-contained and nontrivial. It earns its place but leaves little room for adjacent operations.

Completeness4/5

For the narrow purpose of evaluating agreement across public art records, the tool appears complete, including source fetching and past checks. Minor gaps remain, such as separate evidence-gathering or explanation tools, but core task coverage is present.

Available Tools

1 tool
evaluate_public_art_evidenceCheck public art evidenceA
Read-onlyIdempotent
Inspect

Use this when asked whether public NFT or digital-art records agree (creator, contract, token). Pass a question and evidence_items. Returns AGREES / CONFLICT per field, copies counted once, past checks; fetch_sources: true reads up to 5 pages. No authenticity, ownership or price claim. Free, read-only, no account; inputs must be public and non-personal.

ParametersJSON Schema
NameRequiredDescriptionDefault
questionYesWhat you want to know about the records.
syntheticNoOptional: true marks a test call.
episode_idNoOptional: your own id to group related calls.
fetch_sourcesNoOptional, default false: true lets GAIP read up to 5 https source_url pages (robots.txt honoured) and report whether each page shows its claimed creator, contract, token id and date.
evidence_itemsYesRecords as they appear, each with a source_url (read only when fetch_sources is true).
continuity_handleNoOptional: the continuity_handle from an earlier GAIP result; links this call to your earlier ones.
data_classificationNoPUBLIC (default) or NON_PERSONAL_PUBLIC. Never send personal data.PUBLIC
independent_operator_idNoOptional: your operator id (recorded as a claim, not verified).

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnly/idempotent/openWorld/non-destructive), the description adds substantive behavior: per-field AGREES/CONFLICT output, duplicate copies counted once, prior-check handling, and that fetch_sources reads up to 5 pages with robots.txt honoured. It is also explicit that there is no account requirement and no personal data allowed, which annotations do not convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The key trigger and scope are front-loaded in the first two sentences, and every clause carries information. The later telegraphic fragments ('copies counted once, past checks') are compact but slightly clipped, keeping it just short of fully polished.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly carries the return-value burden by naming the AGREES/CONFLICT per-field result shape. Combined with privacy limits, page-fetch bounds, and stated non-claims, it is complete enough for an agent to call the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 8 parameters, and fetches even the fetch_sources semantics are duplicated in the schema. The description restates the two required params and the fetch_sources behavior but adds no new syntax or format guidance, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb (evaluate/check) and resource (public NFT/digital-art records) and names the exact fields compared (creator, contract, token). It also carves out the boundary explicitly with 'No authenticity, ownership or price claim,' so an agent knows precisely what question this tool does and does not answer.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The trigger condition is stated up front: 'Use this when asked whether public NFT or digital-art records agree.' It also lists exclusions (no authenticity/ownership/price), implied usage of the fetch_sources switch, and constraints (inputs must be public and non-personal), leaving little to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool update
    • Changedevaluate_public_art_evidence2 fields changed
      • changedInput schema / properties / evidence_items / description
        Previous value: -"Records as they appear, each with a source_url (not fetched)."New value: +"Records as they appear, each with a source_url (read only when fetch_sources is true)."
      • addedInput schema / properties / fetch_sources
        Added value: +{
+  "default": false,
+  "description": "Optional, default false: true lets GAIP read up to 5 https source_url pages (robots.txt honoured) and report whether each page shows its claimed creator, contract, token id and date.",
+  "type": "boolean"
+}
  2. 1 tool update
    • Changedevaluate_public_art_evidence7 fields changed
      • addedInput schema / properties / continuity_handle / description
        Added value: +"Optional: the continuity_handle from an earlier GAIP result; links this call to your earlier ones."
      • addedInput schema / properties / data_classification / description
        Added value: +"PUBLIC (default) or NON_PERSONAL_PUBLIC. Never send personal data."
      • addedInput schema / properties / episode_id / description
        Added value: +"Optional: your own id to group related calls."
      • addedInput schema / properties / evidence_items / description
        Added value: +"Records as they appear, each with a source_url (not fetched)."
      • addedInput schema / properties / independent_operator_id / description
        Added value: +"Optional: your operator id (recorded as a claim, not verified)."
      • addedInput schema / properties / question / description
        Added value: +"What you want to know about the records."
      • addedInput schema / properties / synthetic / description
        Added value: +"Optional: true marks a test call."
  3. 1 tool update
    • Changedevaluate_public_art_evidence3 fields changed
      • addedInput schema / examples
        Added value: +[
+  {
+    "evidence_items": [
+      {
+        "chain": "ethereum",
+        "contract": "0xa11ce00000000000000000000000000000000042",
+        "creator": "Artist A",
+        "edition": "1 of 10",
+        "identifier": "7",
+        "name": "Harbour at Dusk",
+        "source": "marketplace_listing",
+        "source_url": "https://opensea.io/assets/ethereum/0xa11ce00000000000000000000000000000000042/7"
+      },
+      {
+        "chain": "eth",
+        "contract_address": "0xA11CE00000000000000000000000000000000042",
+        "mint_date": "2021-03-14T09:26:53Z",
+        "source": "block_explorer",
+        "source_url": "https://etherscan.io/nft/0xa11ce00000000000000000000000000000000042/7",
+        "token_id": "7"
+      },
+      {
+        "artist": "Artist A",
+        "created": "2021",
+        "edition": "1/5",
+        "medium": "Digital painting",
+        "source": "artist_catalogue",
+        "source_url": "https://artist-a.example/catalogue/harbour-at-dusk",
+        "title": "Harbour at Dusk"
+      }
+    ],
+    "question": "Do these public records agree on the creator and the edition?"
+  }
+]
      • addedInput schema / properties / data_classification / default
        Added value: +"PUBLIC"
      • changedInput schema / required
        Previous value: -[
-  "data_classification",
-  "question",
-  "evidence_items"
-]New value: +[
+  "question",
+  "evidence_items"
+]
  4. 1 tool update
    • First observedevaluate_public_art_evidence

Related MCP Connectors

Related MCP Servers

  • Provenio MCP Server

    mildo-ai
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to query a 282,731-node knowledge graph of art market transactions and provenance records, returning cited answers with <1% hallucination and explicit coverage gaps.
    4 npm
    MIT

  • open-museum-mcp

    cfpramod
    A
    license
    A
    quality
    A
    maintenance
    Federated, license-verified search across open-access museum collections — currently The Met, Cleveland, AIC, Wikimedia Commons, and Europeana, with more being added. Strict-default-deny rights gate accepts only CC0 / Public Domain Mark, returning reuse-safe artwork with citations in three styles.
    5
    149 npm
    14
    MIT

  • whatiiif MCP server

    natemoo93
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables agents to find, read, and cite digitized primary sources published via IIIF — searching several institutions' catalogues, resolving item pages to manifests, pulling page images or regions for vision models, and generating citations with rights and provenance. Runs read-only over stateless Streamable HTTP with no login.
    AGPL 3.0

  • art-institute-chicago-mcp

    cyanheads
    A
    license
    Not graded
    quality
    A
    maintenance
    Provides keyless access to the Art Institute of Chicago's public collection data through six tools and an artwork-detail resource, covering search and filtering of artworks, bulk records with provenance/images, artist and exhibition discovery, vocabulary lookup, and audio-guide transcript search.
    64 npm
    1
    Apache 2.0
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources