{"data":{"name":"io.github.cyanheads/eurostat-mcp-server","title":null,"description":"Search and query the Eurostat catalogue — EU economy, demography, trade, and NUTS regional data.","version":"0.10.0","websiteUrl":null,"repositoryUrl":"https://github.com/cyanheads/eurostat-mcp-server","remotes":[{"url":"https://eurostat.caseyjhand.com/mcp","type":"streamable-http"}],"packages":[{"version":"0.10.0","identifier":"@cyanheads/eurostat-mcp-server","runtimeHint":"stdio","registryType":"npm","runtimeArguments":null,"environmentVariables":null},{"version":"0.10.0","identifier":"@cyanheads/eurostat-mcp-server","runtimeHint":"streamable-http","registryType":"npm","runtimeArguments":null,"environmentVariables":null}],"status":"active","isLatest":true,"publishedAt":"2026-10-15T03:10:38.235Z","updatedAt":"2026-10-15T03:10:38.235Z","source":"official-registry","verification":"official","confidence":100,"stars":null,"sources":[{"stars":null,"title":null,"source":"official-registry","sourceId":"io.github.cyanheads/eurostat-mcp-server","updatedAt":"2026-10-15T03:10:38.235Z","confidence":100,"websiteUrl":null,"description":"Search and query the Eurostat catalogue — EU economy, demography, trade, and NUTS regional data.","verification":"official","repositoryUrl":"https://github.com/cyanheads/eurostat-mcp-server"}],"toolIndex":{"tools":[{"serverName":"io.github.cyanheads/eurostat-mcp-server","endpointFingerprint":"463388fee14186f406bf943fd00fab35d17154d5e161fce795dc9464cff2476e","name":"eurostat_browse_themes","title":"Browse Eurostat Theme Hierarchy","description":"Navigate the Eurostat theme tree, for discovery when you know the domain but not the dataset code; eurostat_search_datasets finds datasets by keyword. Without theme_code it returns the top-level theme folders, with one that folder's immediate subfolders and datasets. The tree is the dissemination table of contents plus the Comext host's DS-* collections: detailed trade under ext_go_detail (in ext_go) and PRODCOM under prom (in icts). A collection on neither, such as the legacy PRODCOM DS-056120, is not disseminated and appears nowhere in the tree.","inputSchema":{"type":"object","properties":{"theme_code":{"description":"Folder code to expand (e.g., \"economy\", \"reg\"), matched exactly, then ignoring case. Omit for the top-level folders.","type":"string"}},"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":false},"annotations":{"readOnlyHint":true,"idempotentHint":true,"openWorldHint":true},"definitionHash":"9626553837ce32c06f88e422e7cce99ce1053b5ba2708c6bad6f9777331ee8ed","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T07:46:36.114Z","metadataTrust":"untrusted"},{"serverName":"io.github.cyanheads/eurostat-mcp-server","endpointFingerprint":"463388fee14186f406bf943fd00fab35d17154d5e161fce795dc9464cff2476e","name":"eurostat_dataframe_describe","title":"Describe Eurostat Dataframes","description":"List the tables on a Eurostat dataframe canvas with row counts and column names and types; call it before eurostat_dataframe_query for the names to write SQL against, and read the columns here rather than assuming them. eurostat_query_dataset tables give each dimension a code column (e.g. \"geo\") and a label column (\"geo_label\"); eurostat_download_dataset tables carry code columns only, plus \"time\". Both write the same measure columns (obs_value, obs_flag, obs_flag_label, conf_status, conf_status_label) with the same codes, so they join on dimension codes and time; DS-* tables add obs_value_text for a value published as text. A eurostat_get_dimension_values table has code and label, plus level for geo (NULL for a code with no NUTS level), and labels a download's codes through a join (d.geo = g.code); staged without geo_level, a geo list holds every level, so filter level before aggregating.","inputSchema":{"type":"object","properties":{"canvas_id":{"type":"string","pattern":"^[A-Za-z0-9_-]{10}$","description":"The canvasId a eurostat_query_dataset, eurostat_download_dataset or eurostat_get_dimension_values response returned."}},"required":["canvas_id"],"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":false},"annotations":{"readOnlyHint":true,"idempotentHint":true,"openWorldHint":false},"definitionHash":"540f81501a07fc28b0743dacb66951d776eed0a0b6ca4604d7b505365cfb8d35","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T07:46:36.114Z","metadataTrust":"untrusted"},{"serverName":"io.github.cyanheads/eurostat-mcp-server","endpointFingerprint":"463388fee14186f406bf943fd00fab35d17154d5e161fce795dc9464cff2476e","name":"eurostat_dataframe_query","title":"Query Eurostat Dataframes","description":"Run one read-only SQL SELECT against the tables staged on a Eurostat dataframe canvas, to reach observations past an inline preview and to aggregate or join them without re-fetching. Call eurostat_dataframe_describe first for the table and column names. Statement chaining, other verbs, and functions that read files or external data are rejected. Returns every complete row up to the canvas row limit.","inputSchema":{"type":"object","properties":{"canvas_id":{"type":"string","pattern":"^[A-Za-z0-9_-]{10}$","description":"The canvasId a eurostat_query_dataset, eurostat_download_dataset or eurostat_get_dimension_values response returned."},"sql":{"type":"string","minLength":1,"description":"One read-only SELECT over the names eurostat_dataframe_describe reports, e.g. SELECT geo, AVG(obs_value) AS mean FROM df_a1b2c3d4 WHERE time >= '2020' GROUP BY geo ORDER BY mean DESC."}},"required":["canvas_id","sql"],"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":false},"annotations":{"readOnlyHint":true,"idempotentHint":true,"openWorldHint":false},"definitionHash":"a2e0699c0fbeb53a0a6d49867cd73816c3e397009b8dc6f1a366305d8dbee449","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T07:46:36.114Z","metadataTrust":"untrusted"},{"serverName":"io.github.cyanheads/eurostat-mcp-server","endpointFingerprint":"463388fee14186f406bf943fd00fab35d17154d5e161fce795dc9464cff2476e","name":"eurostat_download_dataset","title":"Download Eurostat Dataset","description":"Download a Eurostat dataset through the SDMX bulk TSV endpoint and stage it as a SQL table on the dataframe canvas — the route to a whole dataset, where eurostat_query_dataset is the route to a slice. It is expanded into one row per non-blank TSV cell; absentCellCount says which rows are not observations. Filter keys come from eurostat_get_dataset_info and values from eurostat_get_dimension_values. Two budgets bound every transfer: a decoded-byte budget (50 MiB by default) and a time budget counted from the start of the call (55 seconds by default, inside the 60 seconds an MCP client waits), so a download that reaches the time budget returns after about 55 seconds. Reached after rows have streamed, either budget keeps them as a prefix with budgetExceeded set; reached before the first row, the call fails. Only preview_limit rows come back inline; without a canvas the rest are not kept.","inputSchema":{"type":"object","properties":{"dataset_code":{"type":"string","minLength":1,"description":"Dataset code (e.g., \"nama_10_gdp\"). Filter a DS-* code (Comext trade or PRODCOM, in any case): an unfiltered download of a large collection is refused as extraction_too_big, and its trade flows mix annual and monthly series, so filter freq."},"filters":{"default":{},"description":"Map of dimension code → values to keep, e.g. {\"unit\": [\"CP_MEUR\"], \"geo\": [\"DE\", \"FR\"]}. Keys match in any case; a key the dataset lacks, \"time\" included (use since_period/until_period), is rejected with its dimension list. An empty array or a blank value is no filter. A value holding \"+\" is split into separate values (OR). A value holding \".\" is rejected as invalid_dimension before any request: no Eurostat code contains one. A value Eurostat does not know fails the download as invalid_dimension; a valid one with no observation in the selected periods is named in emptyValues.","type":"object","propertyNames":{"type":"string"},"additionalProperties":{"type":"array","items":{"type":"string"}}},"since_period":{"description":"Start of the range, inclusive: YYYY, YYYY-MM, YYYY-MM-DD, YYYY-Qn (1–4), YYYY-Sn (1–2), YYYY-Tn (1–3), YYYY-Mnn (01–12), YYYY-Wnn (up to 53) or YYYY-Dnnn (up to 366), e.g. \"2020\", \"2023-Q1\", \"2024-01\". A range is the most effective way to shrink a download. Any form works on any dataset, but Eurostat keeps only periods wholly inside the range, per frequency: a bound that falls inside a period excludes it, and a notice names that period when the TSV header shows its frequency. A one-day range (both bounds on the same day) selects that day alone. A malformed or non-existent period, or a since_period after until_period, fails as invalid_period.","type":"string"},"until_period":{"description":"End of the range, inclusive (e.g., \"2024\"), in the forms and under the wholly-inside rule of since_period. Omit for data through the latest period.","type":"string"},"preview_limit":{"default":25,"description":"Rows echoed inline, from the start of the download. Default 25; positive integers above 500 are clamped to 500 with a notice. The staged table, when there is one, holds every row.","type":"number","minimum":1,"multipleOf":1},"canvas_id":{"description":"A canvasId from an earlier staging response, to stage this download beside its tables for joins; omit for a fresh canvas.","type":"string","pattern":"^[A-Za-z0-9_-]{10}$"}},"required":["dataset_code"],"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":false},"annotations":{"readOnlyHint":true,"idempotentHint":true,"openWorldHint":true},"definitionHash":"a227931bef876c466c505dada2da96b1a9bb3327b211c491a7e3b01b52d65982","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T07:46:36.114Z","metadataTrust":"untrusted"},{"serverName":"io.github.cyanheads/eurostat-mcp-server","endpointFingerprint":"463388fee14186f406bf943fd00fab35d17154d5e161fce795dc9464cff2476e","name":"eurostat_get_dataset_info","title":"Get Eurostat Dataset Info","description":"Fetch a Eurostat dataset's metadata: dimensions with sample values, time range, observation count and last update. Call it before eurostat_query_dataset or eurostat_download_dataset to learn the dimension codes their filters take; the download rejects a filter naming a dimension absent here. Up to 10 sample values per dimension; eurostat_get_dimension_values lists the rest. A DS-* code (detailed trade and PRODCOM, any case) is read from the Comext host, which reports no period coverage or observation count; the first call on a large Comext collection downloads its full structure and takes longer, and repeat calls within the hour reuse it.","inputSchema":{"type":"object","properties":{"dataset_code":{"type":"string","minLength":1,"description":"Dataset code (e.g., \"nama_10_gdp\", or \"DS-045409\" for a Comext collection), from eurostat_search_datasets or eurostat_browse_themes."}},"required":["dataset_code"],"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":false},"annotations":{"readOnlyHint":true,"idempotentHint":true,"openWorldHint":true},"definitionHash":"0ca4634a4edb4343ee8508618cb4a6c33810619e72fd476cc3af498bb52e0743","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T07:46:36.114Z","metadataTrust":"untrusted"},{"serverName":"io.github.cyanheads/eurostat-mcp-server","endpointFingerprint":"463388fee14186f406bf943fd00fab35d17154d5e161fce795dc9464cff2476e","name":"eurostat_get_dimension_values","title":"Get Eurostat Dimension Values","description":"List every value a Eurostat dataset carries in one dimension, with codes and labels exactly as published: when eurostat_get_dataset_info's sample is not enough, or to confirm filter codes before querying. Narrow a long list with filter (words in a code or label) or code_prefix (the codes under a parent, such as one country's regions), and page with cursor. Pass canvas_id to also stage the whole list as a table, to label a download's codes through a join.","inputSchema":{"type":"object","properties":{"dataset_code":{"type":"string","minLength":1,"description":"Dataset code (e.g., \"nama_10_gdp\", or \"DS-045409\" for a Comext collection)."},"dimension":{"type":"string","minLength":1,"description":"Dimension code (e.g., \"geo\", \"unit\"), matched exactly, then ignoring case; TIME_PERIOD aliases time. eurostat_get_dataset_info lists them."},"geo_level":{"description":"NUTS level, for the \"geo\" dimension only (rejected with any other): \"aggregate\" (EU/EA codes), \"country\" (2-letter codes, the inline default), \"nuts1\", \"nuts2\", \"nuts3\".","type":"string","enum":["aggregate","country","nuts1","nuts2","nuts3"]},"filter":{"description":"Words to find, up to 500 characters: keeps values whose code and label, joined by a space, contain every word as a substring, in any order, ignoring case and accents. Punctuation is part of a word; spellings are not transliterated (\"münchen\" does not find MUENCHEN). Applies to the whole list at the effective geo_level before paging, in Eurostat's order.","type":"string","maxLength":500},"code_prefix":{"description":"Keep values whose code starts with this text, ignoring case: the codes under a parent where codes nest by prefix (\"DE\" with geo_level \"nuts2\" lists the German NUTS 2 regions; a CN heading lists its codes, itself included). Aggregates outside the code tree are not reached. Up to 100 characters, no wildcards. Applies at the effective geo_level, with filter, before paging.","type":"string","maxLength":100},"limit":{"default":25,"description":"Values per page, default 25; values above 1,000 clamp to 1,000 with a notice. Fixed by the first call and ignored with cursor.","type":"number","minimum":1,"multipleOf":1},"cursor":{"description":"Opaque nextCursor from the previous page; omit for the first. Bound to dataset_code, dimension (any accepted spelling), geo_level, filter and code_prefix, so send those unchanged.","type":"string"},"canvas_id":{"description":"Also stage the dimension's whole list on this canvas, whatever filter, code_prefix and limit, narrowed only by an explicit geo_level: columns code and label, plus level for geo (NULL for a code with no NUTS level). Without geo_level a geo table holds every level, aggregates and regions beside the countries they contain, so filter level before summing or averaging. Pass the canvasId of a eurostat_query_dataset or eurostat_download_dataset response; this tool never starts a canvas. First call only, not with cursor. Ignored without a dataframe canvas.","type":"string","pattern":"^[A-Za-z0-9_-]{10}$"}},"required":["dataset_code","dimension"],"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":false},"annotations":{"readOnlyHint":true,"idempotentHint":true,"openWorldHint":true},"definitionHash":"a3e942fdac22a6ae4b254f74dfddb0d9488c548d5e1bddad5cdd64a1f71169df","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T07:46:36.114Z","metadataTrust":"untrusted"},{"serverName":"io.github.cyanheads/eurostat-mcp-server","endpointFingerprint":"463388fee14186f406bf943fd00fab35d17154d5e161fce795dc9464cff2476e","name":"eurostat_query_dataset","title":"Query Eurostat Dataset","description":"Fetch a filtered slice of a Eurostat dataset as decoded observations: dimension codes and labels, numeric value, OBS_FLAG status and CONF_STATUS confidentiality marker. Returns a deterministic inline prefix (preview_limit) beside totals over the whole match; filters and period inputs shrink the match itself. Read dimension codes with eurostat_get_dataset_info and their values with eurostat_get_dimension_values first. Filter large slices: Eurostat refuses an oversized query (extraction_too_big) or prepares a large one in the background (async_response). On a deployment with a dataframe canvas, a match above 5,000 observations, or any match with stage=true, is staged as a SQL table (tableName). For a whole dataset, eurostat_download_dataset is the cheaper route.","inputSchema":{"type":"object","properties":{"dataset_code":{"type":"string","minLength":1,"description":"Dataset code (e.g., \"nama_10_gdp\"). DS-* codes (Comext trade and PRODCOM, in any case) work too; their trade flows mix annual and monthly series, so filter freq."},"filters":{"default":{},"description":"Map of dimension code → values to keep, e.g. {\"unit\": [\"CP_MEUR\"], \"geo\": [\"DE\", \"FR\"]}; eurostat_get_dimension_values lists the values. Keys match in any case and must be dimensions: one naming a request control (lang, format, geoLevel, sinceTimePeriod, untilTimePeriod, lastTimePeriod) is rejected as invalid_dimension. An empty array or a blank value is no filter. A value holding \"+\" is split into separate values (OR); one holding \".\" matches nothing, since no Eurostat code contains it. Leave out \"geo\" when geo_level is set, and \"time\"/\"time_period\" when a period input is. A value that matches nothing is named in unmatchedValues, and a valid one with no cell in the selected periods in emptyValues; neither is an error.","type":"object","propertyNames":{"type":"string"},"additionalProperties":{"type":"array","items":{"type":"string"}}},"geo_level":{"description":"NUTS level to keep, mutually exclusive with filters.geo: \"aggregate\" (EU/EA totals), \"country\" (member and candidate states), \"nuts1\", \"nuts2\" or \"nuts3\". A code of the level with no cell in the match is named in emptyValues.","type":"string","enum":["aggregate","country","nuts1","nuts2","nuts3"]},"since_period":{"description":"Start of the range, inclusive: YYYY, YYYY-MM, YYYY-MM-DD, YYYY-Qn (1–4), YYYY-Sn (1–2), YYYY-Tn (1–3), YYYY-Mnn (01–12), YYYY-Wnn (up to 53) or YYYY-Dnnn (up to 366), e.g. \"2020\", \"2023-Q1\", \"2024-01\". Any form works on any dataset, but Eurostat keeps only periods wholly inside the range, per frequency: a bound that falls inside a period excludes it, and a notice names that period when the response shows its frequency. A one-day range (both bounds on the same day) selects that day alone. A malformed or non-existent period, or a since_period after until_period, fails as invalid_period.","type":"string"},"until_period":{"description":"End of the range, inclusive (e.g., \"2024\"), in the forms and under the wholly-inside rule of since_period. Omit for data through the latest period.","type":"string"},"last_n_periods":{"description":"Select the N most recent time positions of the dataset. N counts back from the dataset's latest period, not this slice's, so a slice that lags can come back short or empty; a notice names each selected period with no cell. Mutually exclusive with since_period and until_period.","type":"number","minimum":1,"multipleOf":1},"preview_limit":{"default":25,"description":"Observations returned inline, from the start of the dataset's cell order. Default 25; positive integers above 500 are clamped to 500 with a notice. Shortens only the inline prefix: the counts, timeRange and staged rows still cover the whole match.","type":"number","minimum":1,"multipleOf":1},"stage":{"default":false,"description":"Stage the whole match as a SQL table whatever its size; by default only a match above 5,000 observations is staged. Without a dataframe canvas, a notice says nothing was staged.","type":"boolean"},"lang":{"default":"EN","description":"Language of the labels.","type":"string","enum":["EN","FR","DE"]},"canvas_id":{"description":"A canvasId from an earlier staging response, to stage this result beside its tables for joins; omit for a fresh canvas. Used only when this call stages.","type":"string","pattern":"^[A-Za-z0-9_-]{10}$"}},"required":["dataset_code"],"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":false},"annotations":{"readOnlyHint":true,"idempotentHint":true,"openWorldHint":true},"definitionHash":"2b5ab0893090bc3ea97bf28351a5de33f27e80b813509f2485533ba62d4f151d","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T07:46:36.114Z","metadataTrust":"untrusted"},{"serverName":"io.github.cyanheads/eurostat-mcp-server","endpointFingerprint":"463388fee14186f406bf943fd00fab35d17154d5e161fce795dc9464cff2476e","name":"eurostat_search_datasets","title":"Search Eurostat Datasets","description":"Search the Eurostat catalogue by keyword for dataset codes, with labels, period coverage and theme breadcrumbs; datasets and predefined tables only, no folders. Pass a code to eurostat_get_dataset_info, then eurostat_query_dataset for a slice or eurostat_download_dataset for the whole dataset. The catalogue joins the dissemination table of contents with the Comext host's dataflow list, which adds the DS-* collections (detailed trade by CN8, HS, SITC, BEC and CPA, and PRODCOM); Comext entries report a last-update date but no period coverage or observation count. A collection on neither list, such as the legacy PRODCOM DS-056120, is not disseminated and cannot be reached.","inputSchema":{"type":"object","properties":{"query":{"type":"string","minLength":1,"pattern":"\\S","description":"Search words, at least one. Every word must match, in any order and ignoring case, somewhere in the dataset label, theme breadcrumb or code. Spacing beside punctuation in the catalogue is ignored (\"Rev.2\" finds \"Rev. 2\"); a word keeps its own punctuation (\"R&D\", \"DS-045409\"). When no dataset holds every word, a query of up to 10 distinct words is searched again, each word a dataset lacks also matching at the start of a word in the English label of one of its dimension values (time excluded); those rows carry matchedValues. When nothing matches, the error names the words to drop."},"limit":{"default":20,"description":"Datasets per page, default 20; values above 100 clamp to 100 with a notice. Fixed by the first call and ignored with cursor.","type":"number","minimum":1,"multipleOf":1},"cursor":{"description":"Opaque nextCursor from the previous page; omit for the first. Bound to its query and to the catalogue snapshot that issued it: sent with another query, or after the catalogue refreshes, it is rejected.","type":"string"}},"required":["query"],"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":false},"annotations":{"readOnlyHint":true,"idempotentHint":true,"openWorldHint":true},"definitionHash":"23a3ca68e5060c2b56b7ce08ac8379c04470a005e0d3e63d4a2a0c1ffd60d928","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-19T07:46:36.114Z","metadataTrust":"untrusted"}],"endpoints":[{"endpointFingerprint":"463388fee14186f406bf943fd00fab35d17154d5e161fce795dc9464cff2476e","protocol":"streamable-http","status":"indexed","toolCount":8,"observedAt":"2026-11-19T07:46:36.114Z"}],"authentication":"unknown"},"connectionConfigurations":{"status":"ready","authentication":"not embedded","clients":{"Claude Desktop":{"mcpServers":{"io.github.cyanheads/eurostat-mcp-server":{"url":"https://eurostat.caseyjhand.com/mcp"}}},"Cursor":{"mcpServers":{"io.github.cyanheads/eurostat-mcp-server":{"url":"https://eurostat.caseyjhand.com/mcp"}}},"VS Code":{"servers":{"io.github.cyanheads/eurostat-mcp-server":{"type":"http","url":"https://eurostat.caseyjhand.com/mcp"}}}}},"resourceType":"mcp-server","callable":true,"runtime":{"callable":true,"protocols":["mcp"]},"interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://eurostat.caseyjhand.com/mcp"},{"protocol":"mcp","package":"@cyanheads/eurostat-mcp-server","registryType":"npm","version":"0.10.0"},{"protocol":"mcp","package":"@cyanheads/eurostat-mcp-server","registryType":"npm","version":"0.10.0"}],"profile":{"apiVersion":"1","schemaVersion":"1","id":"mcp-server:io.github.cyanheads%2Feurostat-mcp-server","resourceType":"mcp-server","canonicalUrl":"https://www.agentsjunction.com/api/v1/servers/io.github.cyanheads%2Feurostat-mcp-server","name":"io.github.cyanheads/eurostat-mcp-server","description":"Search and query the Eurostat catalogue — EU economy, demography, trade, and NUTS regional data.","interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://eurostat.caseyjhand.com/mcp"},{"protocol":"mcp","package":"@cyanheads/eurostat-mcp-server","registryType":"npm","version":"0.10.0"},{"protocol":"mcp","package":"@cyanheads/eurostat-mcp-server","registryType":"npm","version":"0.10.0"}],"capabilities":[],"identity":{"source":"official-registry","websiteUrl":null,"repositoryUrl":"https://github.com/cyanheads/eurostat-mcp-server","version":"0.10.0"},"verification":{"state":"official","confidence":100},"operations":{"resourceType":"mcp-server","name":"io.github.cyanheads/eurostat-mcp-server","status":"online","lastCheckedAt":"2026-11-20T09:18:02.106Z","lastSuccessfulCheck":"2026-11-20T09:18:02.106Z","latencyMs":248,"consecutiveFailures":0,"isStale":false,"checks":{"endpointReachable":true,"protocolValid":true,"agentCardValid":null,"mcpHandshakeValid":true},"lastSeen":null,"lastSuccessfulInteraction":null,"lastHealthCheck":"2026-11-20T09:18:02.106Z","source":{"type":"health-check","url":null},"observedAt":"2026-11-20T09:18:02.106Z"},"security":null,"timestamps":{"createdAt":"2026-10-15T03:10:38.235Z","updatedAt":"2026-10-15T03:10:38.235Z","observedAt":"2026-11-20T09:18:02.106Z"},"compatibility":{"serverVersion":"0.10.0","protocolVersions":[{"protocol":"mcp","version":null}]}}}}