MCP ServerBusiness Data with an MCP Server

Business Data with an MCP Server

Worked examples of querying Datafiniti business data through the MCP server — counting, searching, downloading, and running a business prompt.

MCP Server — Business Examples

This guide walks through end-to-end examples of using the MCP Server against business data. It assumes you've already connected a client and authenticated — see the MCP Server guide for setup, transport, and the full tool reference.

Every example here uses the same tools (df_count, df_search, df_start_download, df_download_status) and the same query syntax as the other data types; what changes are the fields and views specific to business records. For the underlying reference, see the Business Data Schema and Constructing Business Queries.

The goal

Say we want hotels in the US, with their locations and contact details — first to size the set, then to pull a targeted sample, and finally to export the full set.

1. Size the result set with df_count

Every tool call names the dataset with a data_type parameter — here "data_type": "business". This is how the server knows to search business records rather than the other data types. The accepted values are property, people, product, and business.

Start with a count. It returns no records and costs no credits, so it's the cheapest way to confirm a query is scoped correctly before spending anything.

{
  "query": "categories:hotels AND country:US",
  "data_type": "business"
}

A response tells you how many records match:

{
  "num_found": 58310
}

Sanity-check the count

A count of 0 is a valid result — no records matched — not an error. If you expected matches, check the category and field names against the schema, then adjust. A count is the cheapest way to test changes before spending credits on a search.

Now retrieve a handful of records. df_search returns up to 50 per call and charges credits identically to REST /search.

{
  "query": "categories:hotels AND country:US AND province:NV",
  "data_type": "business",
  "num_records": 5,
  "view": ["name", "address", "city", "province", "postalCode", "phones", "categories"]
}

The response has the same shape as a REST search — num_found, total_cost, and a records array:

{
  "num_found": 1204,
  "total_cost": 5,
  "records": [
    {
      "name": "…",
      "address": "…",
      "city": "Las Vegas",
      "province": "NV",
      "postalCode": "…",
      "phones": ["…"],
      "categories": ["hotels"]
    }
  ]
}

Quoting exact-match values

Exact-match values use double quotes in the query: name:"Joe's Coffee". That's query syntax, not JSON. A client serializes tool arguments for you; only when you hand-write the JSON do you escape the inner quotes as \". Avoid double-escaping (\\").

3. Search by category and location

Business queries combine field conditions with boolean operators. To find restaurants of a particular cuisine near a location, combine a category with a place:

{
  "query": "categories:restaurants AND categories:Italian AND city:"San Francisco"",
  "data_type": "business"
}

To match more than one category, group alternatives with parentheses:

{
  "query": "categories:(hotels OR motels) AND country:US",
  "data_type": "business"
}

4. Filter on a numeric range

Numeric fields such as revenue accept range syntax. To find businesses within a revenue band:

{
  "query": "categories:restaurants AND country:US AND revenue:[1000000 TO 5000000]",
  "data_type": "business"
}

Ranges work the same way for other numeric and date fields on the record.

5. Export the full set with df_start_download

When you want all matching records rather than a sample, start an asynchronous download. The number of records a download can return is governed by your Datafiniti subscription plan.

{
  "query": "categories:hotels AND country:US",
  "data_type": "business",
  "format": "JSON",
  "view": ["name", "address", "city", "province", "postalCode", "phones", "categories"]
}

This returns a download identifier. Poll it with df_download_status:

{
  "download_id": "…"
}

Once the status comes back complete, the response includes links to the result files.

6. Run a business prompt

Prompts turn a business use-case guide into a ready-to-run query template. For example, discover_business_revenue builds a query for businesses in a revenue band, search_business_by_address looks up a business by street address, and find_restaurants_near_location and search_restaurants_by_cuisine target restaurants — then each tells the client whether to call df_search or df_start_download next.

For the full list of business prompts, see Business Data with AI.

Next steps

Was this page helpful?