MCP 服务器

Free Official Data Samples, Provenance, Aggregations & Insights

com.cazimedia.agentnative/official-provenance-aggregations-insights-free-samples-open-data
数据与分析 搜索与研究 公开且可连接 MCP 2026-07-28

此 MCP 可以做什么

Provides free samples, provenance, aggregations and query access for normalized official datasets and Federal Register records.

aggregate_imported_dataset
Aggregate an official dataset
Use this paid read-only tool for deterministic grouped statistics instead of downloading rows and calculating locally. Returns bounded count, sum, average, minimum, or maximum groups with dataset provenance.
只读 幂等
输入模式
{'type': 'object', 'required': ['dataset_id', 'group_by'], 'properties': {'top': {'type': 'integer', 'maximum': 50, 'minimum': 1}, 'field': {'type': 'string'}, 'metric': {'enum': ['count', 'sum', 'avg', 'min', 'max']}, 'group_by': {'type': 'string'}, 'dataset_id': {'type': 'string'}}, 'additionalProperties': False}
get_coverage_status
Get public-data coverage status
Use this free operational tool to decide whether available public-data coverage is sufficient or whether to request a missing capability. Returns discovery, materialization, queryable-row, queue, failure, and freshness counts.
只读 幂等
输入模式
{'type': 'object', 'properties': {}, 'additionalProperties': False}
get_materialization_status
Check dataset materialization
Poll a durable materialization job. A complete result includes the query-ready dataset ID plus free sample and paid query URLs.
只读 幂等
输入模式
{'type': 'object', 'required': ['materialization_id'], 'properties': {'materialization_id': {'type': 'string', 'pattern': '^job_[a-f0-9]{24}$'}}, 'additionalProperties': False}
list_imported_datasets
List queryable official datasets
Use this free tool when an agent needs only datasets that can be sampled or queried now. Returns fully published warehouse snapshots with dataset IDs, row counts, freshness, and provenance.
只读 幂等
输入模式
{'type': 'object', 'properties': {}, 'additionalProperties': False}
list_official_sources
List official government sources
Use this free tool to inspect which federal, state, city, police, education, and other official source scopes AgentNative currently covers. Returns each source's importer, discovery state, and materialized coverage; it does not return dataset rows.
只读 幂等
输入模式
{'type': 'object', 'properties': {}, 'additionalProperties': False}
query_imported_dataset
Query an imported official dataset
Use this paid read-only tool after sample_imported_dataset confirms the data is suitable. Returns up to 100 normalized rows from a published snapshot with bounded pagination, one exact-match filter, freshness, and provenance.
只读 幂等
输入模式
{'type': 'object', 'required': ['dataset_id'], 'properties': {'top': {'type': 'integer', 'maximum': 100, 'minimum': 1}, 'skip': {'type': 'integer', 'maximum': 5000, 'minimum': 0}, 'dataset_id': {'type': 'string'}, 'filter_field': {'type': 'string'}, 'filter_value': {'type': 'string'}}, 'additionalProperties': False}
query_us_federal_register
Query the US Federal Register
Use this paid read-only tool when the free Federal Register briefing is insufficient. Returns up to 100 normalized official records filtered by date or document type, with deterministic provenance and direct source URLs.
只读 可访问外部资源 幂等
输入模式
{'type': 'object', 'properties': {'top': {'type': 'integer', 'maximum': 100, 'minimum': 1}, 'type': {'enum': ['NOTICE', 'PRORULE', 'RULE', 'PRESDOCU'], 'type': 'string'}, 'end_date': {'type': 'string', 'pattern': '^\\d{4}-\\d{2}-\\d{2}$'}, 'start_date': {'type': 'string', 'pattern': '^\\d{4}-\\d{2}-\\d{2}$'}}, 'additionalProperties': False}
request_capability
Request a missing data capability
Use this state-changing tool only when existing discovery and coverage tools cannot satisfy the task. Records demand for a missing dataset, aggregation, insight, filter, freshness level, or export; repeated requests increase autonomous build priority.
输入模式
{'type': 'object', 'required': ['dataset', 'capability'], 'properties': {'dataset': {'type': 'string', 'maxLength': 100, 'minLength': 2}, 'capability': {'enum': ['dataset', 'filter', 'aggregation', 'insight', 'freshness', 'export'], 'type': 'string'}, 'source_url': {'type': 'string', 'format': 'uri'}, 'example_query': {'type': 'string', 'maxLength': 240}}, 'additionalProperties': False}
request_dataset_materialization
Make a discovered dataset query-ready
Queue a discovered official dataset for prioritized detached ingestion. This free idempotent operation returns a durable job ID; poll get_materialization_status until it supplies sample and query URLs.
幂等
输入模式
{'type': 'object', 'required': ['discovered_dataset_id'], 'properties': {'discovered_dataset_id': {'type': 'string', 'pattern': '^disc_[a-f0-9]{24}$', 'description': 'Exact catalog ID returned by search_discovered_datasets.'}}, 'additionalProperties': False}
request_paid_access
Create a Stripe access checkout
Use this state-changing tool only after free samples demonstrate value and the human owner approves payment. Creates a Stripe Checkout plus one-time claim URL; choose the $5 pass for research or $5/month subscription for recurring workflows.
可访问外部资源
输入模式
{'type': 'object', 'properties': {'plan': {'enum': ['pass', 'subscription'], 'type': 'string', 'default': 'pass'}}, 'additionalProperties': False}
sample_imported_dataset
Sample an official dataset for free
Use this free tool to evaluate a query-ready official dataset before paying. Returns three normalized rows, deterministic summaries, freshness, and provenance; use query_imported_dataset only after the sample proves useful.
只读 幂等
输入模式
{'type': 'object', 'required': ['dataset_id'], 'properties': {'dataset_id': {'type': 'string', 'description': 'Exact query-ready dataset ID returned by list_imported_datasets.'}}, 'additionalProperties': False}
sample_us_federal_register
Get a free Federal Register briefing
Use this free no-auth tool for current US regulatory activity or to evaluate AgentNative before paying. Returns three Federal Register records plus deterministic aggregates over the latest 25 documents, direct record URLs, provenance, and rate-limit status.
只读 可访问外部资源 幂等
输入模式
{'type': 'object', 'properties': {}, 'additionalProperties': False}
search_discovered_datasets
Search discovered government datasets
Use this free tool to find datasets across all discovered official sources, including candidates not yet queryable. Returns catalog matches and materialization state; use list_imported_datasets when only query-ready data is acceptable.
只读 幂等
输入模式
{'type': 'object', 'properties': {'limit': {'type': 'integer', 'maximum': 100, 'minimum': 1, 'description': 'Maximum matches to return; defaults to the service limit.'}, 'query': {'type': 'string', 'maxLength': 100, 'description': 'Optional title or description keywords.'}, 'source_id': {'type': 'string', 'maxLength': 100, 'description': 'Optional exact official source ID returned by list_official_sources.'}}, 'additionalProperties': False}
search_public_datasets
Search public datasets
Use this free tool first when an agent needs official US federal data but does not yet know the dataset ID. Searches normalized catalog metadata and returns matching datasets with provenance; it does not query dataset rows.
只读 可访问外部资源 幂等
输入模式
{'type': 'object', 'required': ['query'], 'properties': {'query': {'type': 'string', 'minLength': 1, 'description': 'Plain-language topic, agency, or dataset keywords, such as employment, schools, or air quality.'}}, 'additionalProperties': False}
已更改
request_paid_access
2026年9月21日 02:59
已添加
query_us_federal_register
2026年9月17日 12:34
已添加
request_paid_access
2026年9月17日 12:34
已添加
request_capability
2026年9月17日 12:34
已添加
aggregate_imported_dataset
2026年9月17日 12:34
已添加
query_imported_dataset
2026年9月17日 12:34
已添加
sample_us_federal_register
2026年9月17日 12:34
已添加
sample_imported_dataset
2026年9月17日 12:34
已添加
list_imported_datasets
2026年9月17日 12:34
已添加
get_coverage_status
2026年9月17日 12:34
已添加
search_discovered_datasets
2026年9月17日 12:34
已添加
list_official_sources
2026年9月17日 12:34
已添加
get_materialization_status
2026年9月17日 12:34
已添加
request_dataset_materialization
2026年9月17日 12:34
已添加
search_public_datasets
2026年9月17日 12:34