smithsonian-mcp-server

v0.3.6 pre-1.0

Search 14.5M Smithsonian Open Access objects across 20+ museums via MCP, and retrieve CC0 images for the 5.2M that carry openly-licensed media. STDIO or Streamable HTTP.

smithsonian.caseyjhand.com/mcp
claude mcp add --transport http smithsonian-mcp-server https://smithsonian.caseyjhand.com/mcp
codex mcp add smithsonian-mcp-server --url https://smithsonian.caseyjhand.com/mcp
{
  "mcpServers": {
    "smithsonian-mcp-server": {
      "url": "https://smithsonian.caseyjhand.com/mcp"
    }
  }
}
gemini mcp add --transport http smithsonian-mcp-server https://smithsonian.caseyjhand.com/mcp
{
  "mcpServers": {
    "smithsonian-mcp-server": {
      "command": "bunx",
      "args": [
        "mcp-remote",
        "https://smithsonian.caseyjhand.com/mcp"
      ]
    }
  }
}
{
  "mcpServers": {
    "smithsonian-mcp-server": {
      "type": "http",
      "url": "https://smithsonian.caseyjhand.com/mcp"
    }
  }
}
curl -X POST https://smithsonian.caseyjhand.com/mcp \
  -H "Content-Type: application/json" \
  -H "MCP-Protocol-Version: 2026-07-28" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2026-07-28","capabilities":{},"clientInfo":{"name":"curl","version":"1.0.0"}}}'

Tools

6

smithsonian_search_objects

open-world

Recommended first step for open-ended or topic discovery: free-text search across 14.5 million Smithsonian objects, with optional exact filters. Filters narrow by museum unit, object type, indexed date term, culture, geographic place, subject topic, named party, and online/CC0 availability. Returns curated summaries (title, date, museum, thumbnail URL, CC0 flag) with the total match count. The record_id in each result is the identifier for smithsonian_get_object, smithsonian_find_related, and smithsonian_get_media. To browse one exact category — a single museum, culture, date term, object type, or topic — use smithsonian_browse_category instead.

read
invocation
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "smithsonian_search_objects",
    "arguments": {
      "query": "<query>"
    }
  }
}
schema
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Free-text search. Use specific terms for precision (\"Tlingit totem pole\") or broad terms for browsing (\"quilt\")."
    },
    "filters": {
      "description": "Optional structured filters to narrow the search.",
      "type": "object",
      "properties": {
        "unit_code": {
          "description": "Museum unit code (e.g. \"NASM\", \"SAAM\", \"NMAH\", \"NMAAHC\", \"NMAI\", \"NPG\", \"CHNDM\", \"SIL\"); the National Museum of Natural History is indexed under discipline sub-units like \"NMNHBIRDS\" and \"NMNHPALEO\", not a bare \"NMNH\". The full set is enumerable via smithsonian_list_terms (field \"unit_code\").",
          "type": "string"
        },
        "object_type": {
          "description": "Object type term from Smithsonian's controlled vocabulary — commonly plural (e.g. \"Paintings\", \"Photographs\", \"Aircraft\"). Singular everyday forms like \"Painting\" usually return nothing. This field is not enumerable via smithsonian_list_terms; harvest valid values from the object_type field in smithsonian_search_objects results. Matched exactly and case-sensitively, and casing variants are indexed as SEPARATE categories — \"button\" and \"Button\" each hold their own records, and neither casing is reliably the larger — so probe a harvested value's other casings rather than assuming one covers the concept.",
          "type": "string"
        },
        "date": {
          "description": "Indexed date term. Decades (\"1920s\", \"1960s\") are the most common form, but the vocabulary also carries year ranges (\"500-1500\"), century terms (\"21st century\"), and BCE forms (\"-2500\", \"BCE 1000s\"). The value must be an exact term — the full set is enumerable via smithsonian_list_terms (field \"date\").",
          "type": "string"
        },
        "culture": {
          "description": "Culture term from the controlled vocabulary — often plural or qualified (e.g. \"Aztecs\", \"Plains Indian\"). The vocabulary is enumerable via smithsonian_list_terms (field \"culture\").",
          "type": "string"
        },
        "place": {
          "description": "Geographic place (e.g. \"United States of America\"). The full set is enumerable via smithsonian_list_terms (field \"place\").",
          "type": "string"
        },
        "topic": {
          "description": "Subject term from the controlled vocabulary (e.g. \"Quilts\", \"Aviation\"). Matches the topics[] values smithsonian_get_object returns, and is a hard constraint — topic \"Quilts\" matches 1,134 objects where the same word as free text matches 2,677. The full set is enumerable via smithsonian_list_terms (field \"topic\").",
          "type": "string"
        },
        "name": {
          "description": "Indexed named party — maker, collector, donor, issuing authority, or any other role the catalog records. Written surname-first (e.g. \"Warhol, Andy\"). This field is not enumerable via smithsonian_list_terms. A smithsonian_find_related name signal carries the indexed form verbatim and is the reliable source; smithsonian_get_object's makers[] is the catalog's free-text form of the same parties and is often written differently (\"Major J. A. L. Möller (Jacob A.L. Möller/Monty Möller), Non-Indian, 1883-1957\" for the indexed \"Möller, Major J. A. L.\"), so treat it as a starting guess.",
          "type": "string"
        },
        "online_only": {
          "description": "When true, restrict to records carrying an indexed online_media_type value. That vocabulary covers digitized surrogates — finding aids, catalog cards, scanned books, full text, electronic resources — alongside images, 3D models, and video, and the surrogate types often have no deliverable media attached, so a match can still report has_media: false. Read has_media on each result to decide whether smithsonian_get_media will return anything.",
          "type": "boolean"
        },
        "cc0_only": {
          "description": "When true, restrict to records that have CC0-licensed media attached (the Lucene term media_usage:CC0). This selects on media presence, not license status — the roughly 9.2M records it excludes are CC0 too, they simply have nothing digitized. Read has_media on each result to decide whether smithsonian_get_media will return anything.",
          "type": "boolean"
        }
      },
      "additionalProperties": false
    },
    "rows": {
      "default": 20,
      "description": "Page size (default 20, max 100).",
      "type": "integer",
      "minimum": 1,
      "maximum": 100
    },
    "start": {
      "default": 0,
      "description": "Pagination offset — 0-indexed. Use with rows for paging through large result sets.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "query",
    "rows",
    "start"
  ],
  "additionalProperties": false
}
view source ↗

smithsonian_list_terms

open-world

Enumerate the valid term vocabulary for an indexed Smithsonian filter field (unit_code, culture, place, date, online_media_type, topic). Terms are a controlled vocabulary — often plural or qualified (e.g. "Paintings", not "Painting") — so guessed filter values tend to return nothing. Returns a page of the field's distinct term values; large vocabularies (topic has 133k terms, place 114k) page via start and rows. For unit_code, each code is returned with its museum name and contains matches the name as well as the code, so a museum name resolves to its code in one call.

read
invocation
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "smithsonian_list_terms",
    "arguments": {
      "field": "<field>"
    }
  }
}
schema
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "field": {
      "type": "string",
      "enum": [
        "unit_code",
        "culture",
        "place",
        "date",
        "online_media_type",
        "topic"
      ],
      "description": "Indexed field to enumerate. Choices: unit_code (museum codes like \"NASM\"), culture (e.g. \"Aztecs\"), place (geographic terms), date (decade/era values like \"1920s\"), online_media_type (media formats like \"Images\", \"3D Models\"), topic (subject terms like \"Quilts\" — 133k terms, so pair it with contains)."
    },
    "start": {
      "default": 0,
      "description": "Pagination offset (0-indexed). Use with rows to page through large vocabularies.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "rows": {
      "default": 50,
      "description": "Number of terms to return per page (default 50, max 100).",
      "type": "integer",
      "minimum": 1,
      "maximum": 100
    },
    "contains": {
      "description": "Case-insensitive substring filter on the term vocabulary — resolve a filter value (e.g. \"greek\") to its exact controlled-vocabulary term(s). For unit_code the substring also matches each code's museum name, so \"National Air and Space\" resolves to \"NASM\".",
      "type": "string"
    }
  },
  "required": [
    "field",
    "start",
    "rows"
  ],
  "additionalProperties": false
}
view source ↗

smithsonian_get_object

open-world

Fetch a normalized catalog metadata projection for a Smithsonian object by its record_id (from smithsonian_search_objects results). Returns the exposed catalog fields — title, dates, description, makers, materials, dimensions, places, cultures, topics, exhibitions, credit line, identifiers, rights, and a media summary. The media summary is a count; full image URLs come from smithsonian_get_media.

read
invocation
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "smithsonian_get_object",
    "arguments": {
      "id": "<id>"
    }
  }
}
schema
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Object record_id from smithsonian_search_objects results (e.g. \"nasm_A19670093000\")."
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}
view source ↗

smithsonian_get_media

open-world

Return every CC0 (open-access) image for a Smithsonian object at multiple resolutions. The tool never returns an empty list — it names the reason instead: an object with nothing digitized, an object whose media is entirely non-image (scanned books, 3D models, sound recordings), and an object whose images are entirely non-CC0 each fail with their own reason. Each image entry includes thumbnail (~120px), screen-size (~800px), and high-resolution JPEG/TIFF URLs with pixel dimensions. The cc0_only filter on smithsonian_search_objects surfaces objects that have downloadable CC0 images.

read
invocation
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "smithsonian_get_media",
    "arguments": {
      "id": "<id>"
    }
  }
}
schema
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "record_id of the object (e.g. \"nasm_A19670093000\") from smithsonian_search_objects or smithsonian_get_object."
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}
view source ↗

smithsonian_browse_category

open-world

Browse Smithsonian objects within one exact category — a single museum (mode "museum"), culture, indexed date term (mode "period"), object type (mode "medium"), or subject term (mode "topic"). The value must be an exact indexed category term, not free text: resolve museum, culture, period, and topic vocabulary with smithsonian_list_terms first (object_type is not enumerable there — harvest it from smithsonian_search_objects results, and treat each casing as its own category, since a harvested object_type covers only the casing it was written in). Returns the category total count, a page of matching objects, and a museum breakdown of that page; page the full category with start and rows. For open-ended or topic discovery, start with smithsonian_search_objects instead.

read
invocation
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "smithsonian_browse_category",
    "arguments": {
      "mode": "<mode>",
      "value": "<value>"
    }
  }
}
schema
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "enum": [
        "museum",
        "culture",
        "period",
        "medium",
        "topic"
      ],
      "description": "Browse dimension: \"museum\" (by unit code), \"culture\" (by culture term), \"period\" (by indexed date term like \"1940s\" or \"500-1500\"), \"medium\" (by object type like \"Paintings\"), \"topic\" (by subject term like \"Quilts\")."
    },
    "value": {
      "type": "string",
      "description": "Category value appropriate to the mode. museum: a unit code like \"NASM\", \"SAAM\", or \"NMNHBIRDS\", matched literally and case-sensitively — not a museum name. culture: term, often plural or qualified (\"Aztecs\", \"Plains Indian\"). period: an indexed date term — commonly a decade (\"1940s\", \"1860s\"), but year ranges (\"500-1500\"), century terms (\"21st century\"), and BCE forms (\"-2500\", \"BCE 1000s\") are indexed too. medium: object type, usually plural (\"Paintings\", \"Aircraft\"). topic: subject term (\"Quilts\", \"Aviation\"). Smithsonian uses a controlled vocabulary — for museum (unit_code), culture, period (date), and topic, call smithsonian_list_terms to find exact terms; medium (object_type) is not enumerable there, so harvest it from smithsonian_search_objects results. Every mode matches its value exactly and case-sensitively, and for medium that split is load-bearing: casing variants are indexed as SEPARATE categories, each reporting its own total_count (\"button\" and \"Button\" are different categories, and neither casing is reliably the larger), so browse the variants of a harvested value rather than assuming one covers the concept."
    },
    "rows": {
      "default": 10,
      "description": "Number of sample objects to return (default 10, max 50).",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "start": {
      "default": 0,
      "description": "Pagination offset — 0-indexed. Page contiguously with start = page × rows.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "mode",
    "value",
    "rows",
    "start"
  ],
  "additionalProperties": false
}
view source ↗