
Monitly
Official statistics for AI agents: Eurostat, World Bank, OECD, IMF and WHO data for 150+ countries.
What it can do
What data it sees
Do you need an account
An API key from the service settings is required
Official statistics for AI agents: Eurostat, World Bank, OECD, IMF and WHO data for 150+ countries.
How to connect
How to connect Monitly to Claude
The server address to paste into Claude settings:
https://monit.ly/api/mcp
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect Monitly to ChatGPT
The server address to paste into ChatGPT settings:
https://monit.ly/api/mcp
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect Monitly to Cursor
The server address to paste into Cursor settings:
https://monit.ly/api/mcp
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (21)
Raw names from tools/list. Only developers need these.
| search_catalog | Find statistical datasets in the catalog (Eurostat, World Bank, OECD, etc.). Index-backed hybrid search (name/code + embeddings). Optional country and source_name filters. Use this instead of SELECT … FROM main ILIKE. Returns compact cards, not series values. |
| search_datasets | Alias of search_catalog. Find statistical datasets by query, optional country and source_name. |
| inspect_dataset | Peek one dataset by main.id: default slice, whether a country is in the series, dataId, and the last few values. Uses indexed main_id lookup — do not scan the data table yourself for discovery. |
| get_dataset | Get one dataset metadata row from main by id (includes dimensions, default_view, geos). |
| execute_sql | Run a read-only SELECT (or WITH … SELECT) against tables main and data only. Use after search_catalog + inspect_dataset to pull the time series for a known data.id / main_id. |
| list_plans | List Monitly plans (Essential, Pro, Enterprise) with prices and limits. |
| get_plan | Current plan of the key owner: name, status, period end and limits (API/day, MCP/month, watchlist, API keys). |
| get_usage | MCP queries this billing period, REST API requests today and watchlist slots — used, limit, remaining. |
| upgrade_plan | Create a Stripe Checkout session for the Pro plan and return checkout_url. Open it in the browser for the user to pay. |
| list_watchlist | Datasets the user follows (watchlist) with source, latest period and alert status. Paginate with limit/offset. |
| add_to_watchlist | Follow a dataset by id (from search_catalog). The user gets alerts when it updates. Respects the plan's watchlist limit. |
| add_watchlist_batch | Follow up to 100 datasets in one call. Skips duplicates and stops at the plan limit (reported in skipped_limit). |
| remove_from_watchlist | Unfollow a dataset by id. |
| set_notification_preferences | action='get' returns e-mail/Slack alert settings. action='set' changes email_notifications / slack_notifications, or turns alerts for one followed dataset on/off (dataset_id + dataset_notifications). |
| list_api_keys | Active REST API keys (mon_…) of the account: id, name, prefix, created/last used. |
| create_api_key | Create a REST API key (mon_…) for /api endpoints. The raw key is returned once. Limit: 3 (Essential) / 10 (Pro). |
| delete_api_key | Revoke a REST API key by id. The last remaining key cannot be deleted. |
| list_mcp_keys | Active MCP keys (mcpk_…). The key used for this session is marked current=true. |
| create_mcp_key | Create another MCP key (mcpk_…), e.g. for a second client. The raw key is returned once. |
| delete_mcp_key | Revoke an MCP key by id. The key used for the current session cannot be revoked here. |
| export_dataset | Return a CSV download URL for a dataset, optionally filtered by countries and dimension values (dim1…dim8 from inspect_dataset). |