INSEE Dataset Observations: Prices, Accounts, Population Figures (Melodi)
insee/dataset-observations
Returns observations of one INSEE dataset (from insee/dataset-list): each with its dimensions (period, geography, product and so on), the value and its status. Narrow by frequency (A annual, Q quarterly, M monthly), geography code, and a first and last period. Returns at most max_result observations (default 20, up to 200) and can report how many the filter matches in total. A dimension the dataset does not have (for example geo on a dataset without one) is refused. Source: Insee, Licence Ouverte 2.0; figures unaltered; served by Eden Engine, not an official INSEE product.
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
INSEE (Institut national de la statistique et des etudes economiques)
Source : Insee, Licence Ouverte 2.0 (Etalab, https://www.etalab.gouv.fr/licence-ouverte-open-licence/). Figures passed through unaltered; the date of the last update is the `modified` field of insee/dataset-info. Served by Eden Engine; not an official INSEE 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.
// 1. search: find the tool
omnial_search({ query: "what you need" })
// 2. inspect: price and input schema
omnial_inspect({ tool: "insee/dataset-observations" })
// 3. learn: read the usage guide at runtime
omnial_learn({ tool: "insee/dataset-observations" })
// 4. run: price the exact call first, then run it
omnial_execute({ tool: "insee/dataset-observations", input: { /* see input_schema */ }, dry_run: true })
omnial_execute({ tool: "insee/dataset-observations", input: { /* ... */ } })
// 5. settle: the call is charged when it finishes, nothing to doNot 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 | $0.0026 |
- Updated
- Oct 20, 2026
Input and output schemas
Input schema
{
"type": "object",
"required": [
"dataset_id"
],
"properties": {
"geo": {
"type": "string",
"pattern": "^[A-Za-z0-9_.-]{1,40}$",
"description": "Geography dimension GEO, in the dataset's own coding, for example 2025-FRANCE-F for metropolitan and overseas France in DS_IPC_PRINC. Leave out for all."
},
"freq": {
"enum": [
"A",
"S",
"Q",
"M"
],
"type": "string",
"description": "Frequency dimension FREQ: A annual, S half-yearly, Q quarterly, M monthly. Leave out for all. Datasets without a FREQ dimension are refused."
},
"dataset_id": {
"type": "string",
"pattern": "^[A-Za-z0-9_-]{2,80}$",
"description": "INSEE dataset id from insee/dataset-list, for example DS_IPC_PRINC (consumer prices)."
},
"end_period": {
"type": "string",
"pattern": "^[0-9]{4}(-[0-9]{2}|-Q[1-4])?$",
"description": "Last period, same forms as start_period."
},
"max_result": {
"type": "integer",
"default": 20,
"maximum": 200,
"minimum": 1,
"description": "Most observations to return, 1 to 200. Default 20."
},
"total_count": {
"type": "boolean",
"description": "True to also report how many observations match the filter, in paging.count."
},
"start_period": {
"type": "string",
"pattern": "^[0-9]{4}(-[0-9]{2}|-Q[1-4])?$",
"description": "First period, as YYYY, YYYY-MM or YYYY-Qn (for example 2026-01)."
}
},
"additionalProperties": false
}Output schema
{
"type": "object",
"required": [
"observations"
],
"properties": {
"title": {
"type": "object",
"description": "Dataset title: { en, fr }.",
"additionalProperties": true
},
"paging": {
"type": "object",
"description": "Page links, plus count (the total) when total_count is true.",
"additionalProperties": true
},
"identifier": {
"type": "string",
"description": "The dataset id."
},
"observations": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
},
"description": "Each has dimensions (TIME_PERIOD and others), measures (the value under a name such as OBS_VALUE_NIVEAU, as { value }) and attributes (status, decimals)."
}
},
"additionalProperties": true
}