dpla.archives.search
Search 50M+ digitized items from US libraries, archives, and museums via the Digital Public Library of America. Filter by media type (image, text, sound, moving image), date range, US state, or contributing institution. Results include title, creator, date, type, subject tags, rights, and direct ...
This record as markdown: /tools/io-github-whiteknightonhorse-apibase/dpla.archives.search.md
What dpla.archives.search does on Apibase
AI agents use dpla.archives.search to create or update resources in Apibase, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Apibase environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
q | string | — | Full-text search query across title, description, creator, and subject fields (e.g. "civil war photographs", "Thomas Jefferson") |
page | integer | — | Page number for pagination, starting at 1 (default: 1) |
type | string | — | Filter by media type: image (photographs, drawings), text (books, manuscripts), sound (audio recordings), moving image (film/video), physical object |
state | string | — | Filter by US state name where the item originated or is about (e.g. "Massachusetts", "California") |
date_end | string | — | Filter items created on or before this year (e.g. "1900"). Use with date_begin for a range. |
provider | string | — | Filter by contributing institution name (e.g. "Smithsonian Institution", "The New York Public Library") |
page_size | integer | — | Number of items per page, 1–50 (default: 10) |
date_begin | string | — | Filter items created on or after this year (e.g. "1850"). Use with date_end for a range. |
Parameters from the server's own tool schema.
Why dpla.archives.search is rated Medium
An AI agent can call dpla.archives.search faster than any human can review: one bad instruction and it creates or modifies resources in Apibase by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs dpla.archives.search safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Apibase, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For dpla.archives.search, this is the rule to start with:
dpla.archives.search stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Apibase, apply this rule, and every dpla.archives.search call is checked against it from then on.
Questions about dpla.archives.search
Search 50M+ digitized items from US libraries, archives, and museums via the Digital Public Library of America. Filter by media type (image, text, sound, moving image), date range, US state, or contributing institution. Results include title, creator, date, type, subject tags, rights, and direct links to the original item and thumbnail. Sources include the Smithsonian, Library of Congress, NYPL, state digitization programs, and 2,000+ contributing institutions. Returns facets for top subjects, providers, and types within the result set. It is categorised as a Write tool in the Apibase MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
dpla.archives.search accepts 8 parameters: q, page, type, state, date_end, provider, page_size, date_begin. The full parameter table on this page comes from the server's own tool schema.
Register the Apibase MCP server in PolicyLayer and add a rule for dpla.archives.search: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Apibase. Nothing to install.
dpla.archives.search is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the dpla.archives.search rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for dpla.archives.search. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
dpla.archives.search is provided by the Apibase MCP server (apibase-mcp-client). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Apibase, and thousands of servers like it.
This server
Across the catalogue