Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@utsunomiya-mcp-server show me the schema for the population dataset"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This is an MCP (Model Context Protocol) server that provides access to Utsunomiya city's open data through natural language queries.
List available datasets from Utsunomiya city
Get schema information for specific datasets
Query dataset contents with filtering
Statistical analysis of dataset values
Caching for improved performance
Related MCP server: Datos.gob.es-MCP
Install via pip: pip install utsunomiya-mcp-server
Run directly: utsunomiya-mcp
Add the following configuration to your claude_desktop_config.json:
{
"mcpServers": {
"utsunomiya-open-data": {
"command": "uvx",
"args": [
"--from",
"utsunomiya-mcp-server",
"utsunomiya-mcp"
]
}
}
}Or if you installed it via pip in a specific environment:
{
"mcpServers": {
"utsunomiya-open-data": {
"command": "utsunomiya-mcp",
"args": []
}
}
}The server provides several tools for interacting with Utsunomiya's open data:
list_datasets: Get available datasets
get_dataset_schema: Get schema information for a dataset
query_dataset: Query dataset contents
analyze_dataset: Get statistical analysis of a dataset
Perform statistical analysis on a dataset.
Inputs: dataset_id (required). Returns: object
Get schema information for a specific dataset.
Inputs: dataset_id (required). Returns: object
List available datasets from Utsunomiya city.
Returns a list of available datasets with their IDs, names, and descriptions. Use this to discover what data is available before querying.
Inputs: no named parameters. Returns: result
Query dataset contents with optional filtering.
Inputs: dataset_id (required), limit, filter_column, filter_value. Returns: result
Search for datasets in the Utsunomiya Open Data Catalog.
Inputs: query (required). Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 5 tools
Each tool has a clearly distinct purpose: listing, searching, schema retrieval, querying, and analysis. No overlap in functionality.
All tool names follow a consistent verb_noun pattern using underscore_case (e.g., list_datasets, query_dataset).
5 tools is appropriate for an open data portal, covering essential operations without being too few or too many.
The tool set covers the full lifecycle of dataset interaction: discovery (list/search), metadata (schema), data retrieval (query), and analysis (analyze). No obvious gaps.
Query, explore, and manage your databases through natural conversation.
Query Baselight's public catalog of 70,000+ datasets — finance, demographics, sports, and more.
Ask questions about a CSV in plain English and get answers, charts and cleaned data back.
List datasets, schemas, run APL queries, and use prompts for exploration, anomalies, and monitoring.