Data Bloomington

What the Data Bloomington MCP server does

The Data Bloomington MCP server exposes Bloomington Open Data datasets through MCP. It works with the Socrata catalog at data.bloomington.in.gov and provides three pack-specific tools:

• datasets searches the catalog by keyword and returns each matching dataset’s resource ID, name, description, category, and update date.
• metadata retrieves a dataset’s schema and descriptive information, including columns, types, row count, category, and last-updated value.
• query runs a SoQL request against a dataset identified by its resource ID and returns matching rows as JSON.

A typical workflow starts with datasets, uses the returned resource ID with metadata to understand available columns, and then calls query to retrieve the required records.

How it works

The gateway endpoint is https://gateway.pipeworx.io/data-bloomington/mcp. A client connecting there receives the Bloomington tools plus shared Pipeworx meta-tools. The gateway’s ask_pipeworx tool can route plain-language questions across the broader Pipeworx catalog, including this data source.

The query tool accepts SoQL clauses through where, select, group, and order fields. These values should omit the leading $ normally used in URL query parameters. limit and offset support result-size and pagination control. Queries require the target dataset’s resource ID, such as yv82-z42g.

The Data Bloomington MCP server can also run independently as a local stdio process. In that mode, it exposes only the three Bloomington tools and does not include the gateway’s shared meta-tools or cross-catalog routing.

Setup and configuration

For a gateway connection, add the MCP endpoint to a compatible client:

{
  "mcpServers": {
    "data-bloomington": {
      "url": "https://gateway.pipeworx.io/data-bloomington/mcp"
    }
  }
}

For local execution, use the published npm package with an MCP client configured for stdio:

{
  "mcpServers": {
    "data-bloomington": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-data-bloomington"]
    }
  }
}

The package can also be started directly with npx -y @pipeworx/mcp-data-bloomington. Local stdio execution does not require a Pipeworx account.

Tools and capabilities

datasets is useful when the agent knows a subject but not the corresponding Socrata resource ID. metadata helps determine field names and types before constructing a query. query supports selecting fields, filtering records, grouping results, ordering output, and paginating through rows.

The gateway also provides HTTP access to individual tools. For example, the catalog search can be called at https://gateway.pipeworx.io/v1/tools/data_bloomington_datasets with a JSON query value.

Limitations and notes

Gateway connections list additional shared Pipeworx tools, so the visible tool count is larger than the three Bloomington-specific tools. The exact gateway scope is reported by the MCP initialize response and may change. Local mode avoids those shared tools but also has no ask_pipeworx routing. The available data and metadata depend on the Bloomington Open Data catalog and its dataset updates.