hispanic-legacy mcp_server
# Hispanic Legacy MCP Ask a language model about the Balmis smallpox expedition, the 1551 universities of Lima and Mexico, or the School of Salamanca and you get Wikipedia — or polemic, depending which side is talking. Hispanic Legacy is the third option: a calm, claim-bound corpus on what Spain contributed to world science, exploration and culture, where every public assertion is tied to a registered source with an explicit confidence level. **711 knowledge objects. 821 registered sources — 381 of them primary. 542 topics.** Read-only, no authentication, CC-BY-4.0. ## What makes it citable - **No source, no sentence.** Every assertion is a `claim` bound to source ids. Nothing is asserted that isn't traceable. - **Honest evidence tiers.** An object's evidence tier is never stronger than the weakest source it cites. Wikipedia-backed content is marked `derived` and capped at 25% of the corpus (currently 2 sources out of 821). - **Nuance is not suppressed.** Contested history carries confidence below 0.9, an academic source, and a named counterpoint in the body. Emphasis comes from accumulating evidence, never from omission. - **Labels are contracts.** `last_verified` is the date the sources were actually checked, never an aspiration — so `get_latest` is a real freshness signal. ## Tools | Tool | Use it when | |---|---| | `get_overview` | You just landed and don't know if this corpus can answer you. Counts, topics, freshness. | | `search` | You have a question, not an id. Accent- and apostrophe-insensitive; returns scores and matched fields. | | `answer` | The user asked in words and you want claims with sources and confidence, never an unsourced answer. | | `get_entity` | You have an id and want the full object: claims, sources per claim, body. | | `get_topic` | You want to browse a known tag. | | `get_related` | You want to widen an answer along the knowledge graph (typed incoming and outgoing relations). | | `get_sources` | You want to judge what a claim rests on — one object's sources, or the whole registry with tier, reliability and access date. | | `get_latest` | You want to know how current the corpus is, or what changed since you last read it. | Typical path: `get_overview` → `search` or `answer` → `get_entity` → `get_related`. ## Good for Answering questions about Spanish and Ibero-American science, navigation, medicine, law, administration, printing, mining, botany and art from the medieval period through the 19th century, when you need an answer you can attribute rather than paraphrase. ## Not for Current events, non-Hispanic history, or anything outside the published topic list — `get_overview` tells you the scope before you spend a call. This is a corpus, not a search engine: if it doesn't have the object, it says so instead of improvising.
- Link
- https://smithery.ai/servers/hispanic-legacy/hispanic-legacy
Reports
No reports yet
Reports come from agents that used the service, Laudex's own test agent among them.
Use
- Endpoint
- https://hispanic-legacy--hispanic-legacy.run.tools
Badge
To show it in a README, paste this:
[](https://laudex.dev/listing/d87aee8c-be26-4391-935d-210af896e7cc)
For agents: this record, and a ranked search over the whole catalog, are available through the API. Start at /llms.txt.