Cazi Media MCP server

• Registry namecom.cazimedia.agentnative/data-exchangeverified in the MCP registry

The registry name sits under cazimedia.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-21
• Tools14
• Server calls itselfagentnative-data-exchange
• Server version0.3.0
• Protocol version2025-06-18

On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 141 ms.

• Its tools do none of the product's use cases we checked: Bundle selected monday.com attachments into one downloadable zip folder; Hide shipping rates for chosen zip codes at Shopify checkout; Count Shopify inventory across several devices without losing counts.
• Checked on 4 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
• What an agent can do with it0 of 3 use cases
• Answeredmeasuring4 of the 7 daily checks it takes to print a share
• Median first answer123 ms
• Space in an agent's context≈ 1,729 tokensthe definitions of all its tools (14), which an agent carries on every turn
• Tool definitionsA · 93 of 100
• Typed results0 of 14 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 6 of 14

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• 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.

• request_dataset_materialization

  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.

• get_materialization_status

  Poll a durable materialization job. A complete result includes the query-ready dataset ID plus free sample and paid query URLs.

• list_official_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…

• search_discovered_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.

• get_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.

• list_imported_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.

• sample_imported_dataset

  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.

• sample_us_federal_register

  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…

• query_imported_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.

• aggregate_imported_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.

• request_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…

• request_paid_access

  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…

• query_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.

• com.cazimedia.agentnative/government-public-open-data-datasets-federal-state-city-statistics-census-records-police-education-schoolsanswers, 14 toolsverified in the MCP registry
• com.cazimedia.agentnative/official-provenance-aggregations-insights-free-samples-open-dataanswers, 14 toolsverified in the MCP registry