libofcongress-mcp-server

Browse LOC Collections

libofcongress_browse_collections

Read-only

List and browse Library of Congress curated digital collections. Returns collection names, descriptions, item counts, slugs, and URLs. Optionally filter by keyword. Collections are curated subsets of the digital holdings with specific focuses (e.g., "Civil War Glass Negatives", "Baseball Cards", "WPA Posters"). Use the returned URL to navigate directly to a collection on loc.gov.

Input Schema

Name	Required	Description
`page`	No	1-indexed page number for paginating results.
`limit`	No	Maximum number of collections to return. Default 25. A page holds at most 100 collections: a larger limit (up to 1000) is served as a 100-collection page, and page then counts 100-collection pages.
`query`	No	Optional keyword to filter collections by name or description. Omit to list all collections.

Output Schema

Name	Required	Description
`page`	No	Current 1-indexed page number.
`error`	No	Present when the call failed. Absent on success.
`pages`	No	Total number of pages available.
`total`	No	Total number of matching collections across all pages.
`notice`	No	Recovery hint when results are empty or a page is out of range — suggests broadening the keyword or removing filters — plus disclosure of a capped limit. Absent on ordinary result pages.
`has_next`	No	True when more pages are available after this one.
`totalCount`	No	Total matching collections — mirrors output.total for agent reasoning.
`collections`	No	LOC curated collections matching the keyword filter, or all collections when no keyword is specified.
`effectiveLimit`	No	The page size actually served when limit exceeded the per-call cap of 100. Absent when limit was within the cap.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedOct 14, 2026

changedInput schema / properties / limit / description

Previous value: -"Maximum number of collections to return. Default 25, max 100."New value: +"Maximum number of collections to return. Default 25. A page holds at most 100 collections: a larger limit (up to 1000) is served as a 100-collection page, and page then counts 100-collection pages."

changedInput schema / properties / limit / maximum
```
Previous value: -100New value: +1000
```

addedOutput schema / properties / effectiveLimit

Added value: +{
+  "description": "The page size actually served when limit exceeded the per-call cap of 100. Absent when limit was within the cap.",
+  "type": "number"
+}

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode. Declared by this tool: `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. `upstream_unavailable`: The Library of Congress could not be reached, or answered with an error status, a bot challenge or other HTML page, or an unreadable response instead of its JSON. Other values are possible when a failure originates below the handler."

changedOutput schema / properties / error / properties / data / properties / reason / examples

Previous value: -[
-  "rate_limit_exceeded",
-  "server_busy",
-  "request_timed_out"
-]New value: +[
+  "rate_limit_exceeded",
+  "server_busy",
+  "request_timed_out",
+  "upstream_unavailable"
+]

changedOutput schema / properties / notice / description

Previous value: -"Recovery hint when results are empty or a page is out of range — suggests broadening the keyword or removing filters. Absent on successful result pages."New value: +"Recovery hint when results are empty or a page is out of range — suggests broadening the keyword or removing filters — plus disclosure of a capped limit. Absent on ordinary result pages."

Changed2 schema fields changedOct 14, 2026

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode. Declared by this tool: `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `rate_limit_exceeded`: LOC API rate limit exceeded; requests are blocked for approximately 1 hour. `server_busy`: More Library of Congress requests are queued on this server than can start within this call's time budget. `request_timed_out`: The Library of Congress did not respond within the 50-second request budget. Other values are possible when a failure originates below the handler."

changedOutput schema / properties / error / properties / data / properties / reason / examples

Previous value: -[
-  "rate_limit_exceeded"
-]New value: +[
+  "rate_limit_exceeded",
+  "server_busy",
+  "request_timed_out"
+]

First observedSep 19, 2026

TDQS

A3.7/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description's main added value is the output shape and the URL navigation behavior. It does not mention pagination behavior beyond what the schema says or rate limits.

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?

Front-loaded with the action and resource, then return fields, filtering, and navigation in logical order. Five sentences is slightly more than needed but each adds some value.

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

Completeness4/5

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

Output schema exists so return values needn't be detailed, and the description covers purpose, filtering, and URL navigation. Minor gap is the absence of explicit sibling routing guidance, but overall adequate for a simple read-only listing tool.

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 coverage is 100%, so parameters are fully documented; the description only reinforces the optional keyword filter. Baseline 3 applies since the schema does the heavy lifting.

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?

States a specific verb (list/browse) and resource (LOC curated digital collections), and distinguishes it from search_items/search_newspapers siblings since this enumerates collections rather than items. The clarification that collections are curated subsets with examples makes the resource concrete.

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

Usage Guidelines3/5

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

Explains how to filter optionally and that the returned URL navigates to loc.gov, but never explicitly states when to use this vs search_items or search_subjects. The sibling differentiation is implied by resource type, not spelled out.

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

All libofcongress-mcp-server tools Inspect

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.