# Knoema MCP MCP > Knoema MCP connects your AI agent directly to millions of global statistics, including data from sources like the IMF, World Bank, and UN. You can search for specific economic indicators, retrieve time-series data using mnemonics, and audit metadata on any dataset—all without leaving your chat client. It's designed for deep dives into macroeconomics, demographics, and environmental trends. ## Overview - **Category:** data-analytics - **Price:** Free - **Tags:** global-statistics, time-series-data, economic-indicators, data-retrieval, public-data, forecasting ## Description Trying to map out global market shifts or forecast resource needs used to be a painful process. You’d open ten tabs, cross-reference data between the World Bank site and an academic journal, manually check units, and spend hours just cleaning up time zones. This MCP changes that. Your agent accesses Knoema's entire catalog of official global statistics. Instead of wrestling with separate vendor APIs or stale spreadsheets, you simply ask your AI client for what you need—say, the historical CPI change across three countries over 30 years. The system handles the complexity and pulls the structured time-series data directly into your conversation window. When you connect Knoema via Vinkius, your agent gains immediate access to global data depth, letting you focus on analysis instead of aggregation. ## Tools ### search_datasets Finds overall dataset IDs and metadata by searching general terms, helping you identify the correct source for your statistics. ### get_dataset_metadata Retrieves detailed background information about a source, helping you understand what variables are actually available. ### list_data_topics Provides a list of macro categories available in Knoema, like Economy or Demographics, for initial data scoping. ### get_data_series Fetches specific historical data points once you know the dataset ID and indicator mnemonics. ### list_dataset_regions Shows which geographical areas (countries/zones) have data coverage for a specific dataset. ### list_data_units Lists all measurement types, such as Percentage or USD, ensuring your collected figures are comparable. ### get_latest_dataset_data Pulls the most recently published data points available for any given dataset ID. ### search_data_series Searches across all available datasets to find highly specific indicators using keywords, making discovery much faster. ### list_data_frequencies Lists all possible reporting intervals, such as Annual or Quarterly, to help you scope your query. ### get_knoema_resource Accesses generic frontend resources for general data context retrieval. ## Prompt Examples **Prompt:** ``` Search for datasets about renewable energy in Europe ``` **Response:** ``` I've found 12 datasets related to renewable energy in Europe, including 'Eurostat: Energy statistics' and 'IRENA: Renewable Capacity'. Which one should we analyze? ``` **Prompt:** ``` Get the metadata for dataset 'IMFWEOS2024Oct' ``` **Response:** ``` Retrieved metadata for 'IMF World Economic Outlook (October 2024)'. It contains 45 indicators for 196 countries, covering 1980-2029. Indicators include GDP, Inflation, and Unemployment. ``` **Prompt:** ``` Search for crude oil price series ``` **Response:** ``` I found multiple series for crude oil prices. The most relevant are 'Crude Oil (Brent)' from World Bank and 'WTI Crude' from EIA. Would you like to fetch the latest data for these? ``` ## Capabilities ### Discovering available datasets You can search for specific dataset IDs or browse broad categories like 'Economy' or 'Agriculture' using topics and units. ### Validating indicators and units You verify data sources, checking metadata to confirm the exact time period, measurement units (like USD or Percentage), and available regions before running a query. ### Retrieving historical data series The agent pulls precise, multi-decade time-series numbers for indicators like GDP or Inflation across multiple countries into one result set. ## Use Cases ### Modeling Cross-Sectoral Economic Stress A financial analyst needs to compare US unemployment rates against EU inflation over the last decade. They use `search_data_series` to find both indicators, then run `get_data_series` multiple times, getting a unified view for their risk model. ### Planning Infrastructure Expansion A corporate strategist must assess the market potential in Southeast Asia. They use `list_data_topics` to narrow down demographics and then query `search_datasets` to find relevant population growth stats for target regions. ### Academic Research on Climate Impact A researcher needs environmental metrics. They first list available data units (`list_data_units`) to ensure they are comparing tons of CO2 emissions versus percentage changes before retrieving the actual time-series figures. ### Competitive Analysis for New Markets A business planner needs current market indicators. They use `get_latest_dataset_data` combined with `list_dataset_regions` to pull real-time metrics on specific commodities across their target countries. ## Benefits - You don't waste time comparing dozens of individual vendor sites. By using `search_data_series`, your agent finds a specific indicator like 'Crude Oil Price' across multiple providers in one search. - Stop guessing if the data is comparable. Before fetching numbers, you use `get_dataset_metadata` to audit the source, confirming details like whether the unit is USD or EUR and what country codes are used. - Forget scraping websites for the latest numbers. The `get_latest_dataset_data` tool pulls the most recent official reports directly into your conversation window when you need current context. - The MCP helps narrow down global scope efficiently. If you only care about North America, you use `list_dataset_regions` first, ensuring all subsequent calls are limited to relevant geography. - You can quickly understand what data is available without knowing the source name. Use `search_datasets` and `list_data_topics` together to scope your research by subject matter (e.g., 'Energy' or 'Health'). - The MCP lets you confirm if a dataset supports Annual, Quarterly, or Monthly reporting via `list_data_frequencies`, ensuring your time-series analysis is based on consistent data cadence. ## How It Works The bottom line is that you ask a question in plain English, and the MCP handles all the complex database calls needed to answer it with verifiable statistics. 1. First, connect your AI client and enter your Knoema Client ID and Secret. This authenticates the connection to the service. 2. Next, ask your agent a natural language question—for instance, 'What were the oil prices in 2015?' The agent then translates this into structured calls using tools like `search_data_series`. 3. Finally, you get back the required data payload. The results appear formatted and ready for immediate analysis within your chat client. ## Frequently Asked Questions **How do I find what data topics are available using list_data_topics?** You run `list_data_topics`, and it gives you a structured list of high-level categories, like 'Agriculture' or 'Economy'. This helps scope your search before committing to specific indicators. **What is the difference between search_datasets and search_data_series?** `search_datasets` finds the overall source (the container), giving you metadata. `search_data_series`, however, searches inside all sources to find a specific indicator by keyword. **I need data for 196 countries; should I use list_dataset_regions?** Yes, running `list_dataset_regions` confirms which geographical areas are covered by the dataset you're looking at. This prevents your agent from querying a source that only covers North America. **How do I confirm if data is available monthly or quarterly?** Use `list_data_frequencies`. It shows all valid time intervals (Annual, Quarterly, Monthly), letting you set the correct scope for your time-series query. **How do I use `get_dataset_metadata` to check which variables a dataset contains?** It returns the full structure of the data, telling you exactly what variables are available. This is crucial because it lets you confirm all fields and units before attempting to retrieve any values using other tools. **If I use `get_data_series` with incorrect mnemonics, how does the system handle the error?** The agent reports a specific validation failure. You'll receive an error message detailing exactly which mnemonic failed and why it couldn't be found in the Knoema catalog. **Does `get_latest_dataset_data` provide better performance than using `get_data_series`?** Yes, it is optimized for speed by fetching only the most recent data points. This saves time and reduces payload size when you just need a quick snapshot of current trends. **Where can I find out what measurement types are supported using `list_data_units`?** It provides a comprehensive list of all available units, like USD or percentage. This is useful because it ensures your analysis is correct and you know exactly how the raw figures are measured. **Where do I get my Knoema API credentials?** Visit the **Knoema Developer Portal** (knoema.com/dev), create an application, and you will receive a Client ID and Client Secret. **How can I find a specific dataset ID?** Use the `search_datasets` tool with relevant keywords. The tool will return a list of matching datasets along with their unique IDs. **What is a mnemonic in Knoema?** A mnemonic is a short, human-readable code used to identify a specific data series within a dataset (e.g., 'NGDP' for Nominal GDP).