HDX Dataset Search: Humanitarian Datasets by Topic, Country or Crisis (Humanitarian Data Exchange)

hdx/search-datasets

Searches the Humanitarian Data Exchange (HDX) for datasets on a topic, country or crisis (q, for example ebola or cholera yemen) and returns each match as HDX's full dataset record: name, title, description, source organisation (dataset_source), licence (license_id, license_title, license_url), update frequency, data period, tags and the list of files (resources). Records are large, 4 to 27 KB each. Only datasets under an open licence are returned: cc-by-igo, cc-by, cc-by-sa, hdx-odc-odbl, hdx-odc-by, hdx-pddl and other-pd-nr. Datasets licensed Multiple Licenses, Other or anything else are left out, so count covers open datasets only. Share-alike and ODbL licences oblige you to carry the licence notice. rows is 1 to 10 (default 3) and start skips matches. A query with no open match returns count 0 and an empty results list. Returns metadata, not the data files. Data from the Humanitarian Data Exchange and its contributing organisations, passed through unmodified and served by Eden Engine; not an official Humanitarian Data Exchange product.

activeper callv1

Price

$0.0026 per call

You pay the price shown. If a call turns out to cost more than its quote, you pay the actual price, capped at twice the quote. No monthly minimum. Top-ups start at $5.

Data source

Humanitarian Data Exchange

Source: the dataset's source organisation (dataset_source) via the Humanitarian Data Exchange (HDX, OCHA), data.humdata.org, licence as named by license_id and license_title. Only datasets under an open licence are returned; share-alike and ODbL licences oblige you to carry the licence notice. Served by Eden Engine; not an official Humanitarian Data Exchange product.

Use it

Five steps: search, inspect, learn, run, settle. No per-tool setup; your agent reaches this tool through the meta-tools it already has.

Connect once and your AI can find and run this tool, and any other it needs.

Install it Create an account

agent

// 1. search: find the tool
omnial_search({ query: "what you need" })

// 2. inspect: price and input schema
omnial_inspect({ tool: "hdx/search-datasets" })

// 3. learn: read the usage guide at runtime
omnial_learn({ tool: "hdx/search-datasets" })

// 4. run: price the exact call first, then run it
omnial_execute({ tool: "hdx/search-datasets", input: { /* see input_schema */ }, dry_run: true })
omnial_execute({ tool: "hdx/search-datasets", input: { /* ... */ } })

// 5. settle: the call is charged when it finishes, nothing to do

Not connected yet? Point your MCP client at https://mcp.eden-engine.com/mcp, then copy a config for your client.

Pricing

Every charge this tool can incur.

Charge	Price
Per call	$0.0026

Updated: Oct 20, 2026

Input and output schemas

Input schema

input_schema.json

{
  "type": "object",
  "required": [
    "q"
  ],
  "properties": {
    "q": {
      "type": "string",
      "maxLength": 200,
      "minLength": 1,
      "description": "Search words, for example ebola, cholera yemen or displacement sudan. Matched against titles, descriptions and tags."
    },
    "rows": {
      "type": "integer",
      "default": 3,
      "maximum": 10,
      "minimum": 1,
      "description": "How many datasets to return, 1 to 10. Default 3."
    },
    "start": {
      "type": "integer",
      "maximum": 10000,
      "minimum": 0,
      "description": "How many matches to skip, for the next page: start 3 with rows 3 is the second three. Leave out to start at the best match."
    }
  },
  "additionalProperties": false
}

Output schema

output_schema.json

{
  "type": "object",
  "required": [
    "count",
    "results"
  ],
  "properties": {
    "count": {
      "type": "integer",
      "description": "How many open-licensed datasets match, across all pages."
    },
    "results": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "name",
          "title",
          "license_id"
        ],
        "properties": {
          "name": {
            "type": "string",
            "description": "Dataset identifier; the page is https://data.humdata.org/dataset/<name>."
          },
          "notes": {
            "type": "string",
            "description": "Free-text description; can be long."
          },
          "title": {
            "type": "string",
            "description": "Dataset title."
          },
          "resources": {
            "type": "array",
            "items": {
              "type": "object",
              "additionalProperties": true
            },
            "description": "The dataset's files, each with name, format, description and download url."
          },
          "license_id": {
            "type": "string",
            "description": "Licence id, one of the open allow-list, for example cc-by-igo."
          },
          "license_url": {
            "type": "string",
            "description": "Link to the licence's legal text."
          },
          "dataset_date": {
            "type": "string",
            "description": "Period the data covers, as a range."
          },
          "last_modified": {
            "type": "string",
            "description": "When the data was last changed."
          },
          "license_title": {
            "type": "string",
            "description": "Licence name, for example Creative Commons Attribution International (CC BY)."
          },
          "dataset_source": {
            "type": "string",
            "description": "The organisation or source the data came from; credit it."
          },
          "data_update_frequency": {
            "type": "string",
            "description": "Days between updates as a string; 0 means never, -1 means live."
          }
        },
        "additionalProperties": true
      },
      "description": "One entry per dataset on this page."
    }
  },
  "description": "The open-licensed datasets matching the query, best match first.",
  "additionalProperties": true
}