https://www.eatmundo.com/api/mcp ↗
Cross-cuisine dish equivalence with shared-ingredient evidence: 1,956 dishes, 26 cuisines.
eatmundo is a remote MCP server published at www.eatmundo.com. It has been probed 11 times since 9/12/2026. It answered in 11 of them (100.0%), a near-uninterrupted record. Median response time is 1,136 ms, a delay an agent will notice. It offers a narrow, focused set of 5 tools. On the protocol side it speaks the 2026-07-28 stateless spec.
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
find_similar_dishes — Description truncated mid-sentence ('Use it fo').search_dishes — Parameter 'form' is ambiguous without definition.weekly_menu — Incomplete explanation of constraint handling ('When a constraint cannot be ').Risk: low
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
Tools the server advertised in the latest measurement — measured, not catalog-claimed.
find_similar_dishesFind dishes from other cuisines that are equivalent to a given dish, from eatmundo's scored equivalence graph (11,467 edges over 1,956 recipes from 26 countries). Every edge is evidence-based - shared canonical ingredients - not a language-model guess, and every edge crosses country lines. Use it for "what is the Greek counterpart of lahmacun, and why".
dishstringrequiredcountrystringmin_scoreintegerlimitintegerlangstringsearch_dishesSearch 1,956 dishes from 26 cuisines by text, country, category, preparation technique, or canonical ingredient. Every ingredient in the corpus is linked to a canonical entity, so an ingredient filter also catches translations and spelling variants. Use it to get a slug for the other tools.
querystringcountrystringcategorystringformstringingredientsarraylimitintegeroffsetintegerlangstringget_recipeFull recipe for one dish: steps, FAQ, image credit, and ingredients with PARSED quantities (amount, unit, and a normalised base in grams or millilitres where the quantity is measurable). Count-based lines like "3 onions" carry a gram estimate only where a per-item weight is known.
slugstringrequiredlangstringcompare_dishesCompare two dishes ingredient by ingredient: shared items, what is unique to each, a match score, and - for the 848 pairs that have one - an editorial comparison paragraph in the requested language. Works for any two dishes in the corpus, whether or not they are an edge in the equivalence graph.
astringrequiredbstringrequiredlangstringweekly_menuBuild a menu of up to 7 dinners, either one cuisine per day ("world") or all from one country. Honours diet exclusions (pork, beef, meat, fish, dairy, egg, alcohol), vegetarian/vegan/pescatarian requirements, a prep-time ceiling and a budget mode that reuses ingredients. When a constraint cannot be met it is relaxed and the relaxation is reported, never hidden.
daysintegermodestringcountrystringexclude_countriesarrayexcludearrayrequirestringtime_limitintegerbudgetbooleaninclude_extrasbooleanseedintegerlangstringDerived by comparing consecutive probes — changes in era, protocol version, build and reachability.
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/com-eatmundo-dishes)<a href="https://mcpmetrics.io/servers/com-eatmundo-dishes"><img src="https://mcpmetrics.io/badge/com.eatmundo/dishes/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to seeThe catalog entries whose name and description are closest to this one, found with the same index the search box uses.
Chinese supplier verification via Remote MCP; free resolve, paid Basic/Full evidence via x402.
Premium agentic endpoint for cross-shard-state-sync-mcp.
Not sure what to do after a slip and fall in California? Use this free evidence checker to find out
Read-only verification evidence for paid machine services and buyer policy checks.
Self-hostable shared brain for you and your AI agents — docs, flows, meetings, decisions, rationale
Read-only BSB and WEB Scripture evidence with provenance, context, comparison, and search.
| Run | Era | Modern | ms | Legacy | ms | Versions |
|---|---|---|---|---|---|---|
| 2026-09-13 12:47:19 | Dual-era | 200 | 1022 | 200 | 960 | 2026-07-28 |
| 2026-09-13 10:45:14 | Dual-era | 200 | 904 | 200 | 858 | 2026-07-28 |
| 2026-09-13 08:43:04 | Dual-era | 200 | 1600 | 200 | 1041 | 2026-07-28 |
| 2026-09-13 06:40:42 | Dual-era | 200 | 1084 | 200 | 1113 | 2026-07-28 |
| 2026-09-13 04:35:29 | Dual-era | 200 | 1328 | 200 | 1813 | 2026-07-28 |
| 2026-09-13 01:33:33 | Dual-era | 200 | 1178 | 200 | 1118 | 2026-07-28 |
| 2026-09-12 23:31:36 | Dual-era | 200 | 1162 | 200 | 1136 | 2026-07-28 |
| 2026-09-12 21:29:15 | Dual-era | 200 | 1359 | 200 | 1243 | 2026-07-28 |
| 2026-09-12 19:27:29 | Dual-era | 200 | 1147 | 200 | 1184 | 2026-07-28 |
| 2026-09-12 17:24:09 | Dual-era | 200 | 1338 | 200 | 831 | 2026-07-28 |
Each block is one measurement round. Green: working response. Amber: responded but the server was returning errors (5xx). Red: no response at all.
Each cell is one probe run. Faded cells are incomplete probes — one leg did not answer, so the era is inconclusive.
The two probe legs separately: modern server/discover and legacy initialize.
Comments
Sign in to write a comment
No comments yet. Be the first.