# Agify MCP > Agify gives you demographic intelligence by predicting a person's age based on their first name. You feed it names, and it returns an estimated age range along with statistical metrics about how confident it is in that number. It handles both single lookups and batches of up to ten names, letting you enrich data without ever asking for a birth date. ## Overview - **Category:** developer-tools - **Price:** Free - **Tags:** demographics, age-prediction, data-enrichment, identity-intelligence, name-analysis ## Description Dealing with user profiles often means collecting sensitive personal identifying information (PII). Instead, Agify lets your agent estimate key demographics using only the name and an optional country code. You send in a list of names, or just one name, and get back age predictions. The service doesn't guess; it uses large-scale demographic data to provide a statistical likelihood. This capability is huge for anything from marketing segmentation to building smarter user onboarding flows. When you connect Agify through Vinkius, your AI client can access this intelligence alongside thousands of other tools in the catalog. You get rich data context right where you're working, instantly profiling users without compromising privacy. ## Tools ### predict_age_batch Processes and predicts ages for multiple people using a list of first names up to ten entries long. ### predict_age Predicts a person's age from their first name, with an option to scope the prediction by country. ## Prompt Examples **Prompt:** ``` Predict the age for the name 'Michael'. ``` **Response:** ``` Based on the Agify database, the estimated age for 'Michael' is 44 years old (based on 233,482 data points). ``` **Prompt:** ``` What is the estimated age for 'Isabella' in Italy (IT)? ``` **Response:** ``` In Italy, the name 'Isabella' has an estimated age of 52 years. ``` **Prompt:** ``` Predict the ages for these names: 'John', 'Emma', and 'Liam'. ``` **Response:** ``` I've processed the batch: 'John' is estimated at 51, 'Emma' at 34, and 'Liam' at 21. ``` ## Capabilities ### Predict single-person age Send a first name and receive an estimated age for that individual. ### Batch predict ages Process up to ten names in one go, getting age estimates for the whole group at once. ### Scope by country code Improve prediction accuracy by limiting the name analysis to a specific geographic region (ISO code). ## Use Cases ### Auditing a stale lead list A marketing manager has a spreadsheet of contacts from an old event. Instead of manually guessing or rejecting records, they ask their agent to run `predict_age_batch` on the entire list to see which age demographics are most represented. ### Developing smart onboarding A developer needs to build a new user flow. They use `predict_age` to check a potential user's name against their intended region, allowing the system to pre-select relevant features or content immediately upon login. ### Market research profiling A product team needs to test different messaging angles. They pipe names from an internal database into `predict_age` to quickly segment users into age groups and see which message resonates best with each demographic. ## Benefits - Build smarter personalization logic. You can use the `predict_age` tool to estimate user ages, allowing your application to tailor content even before sign-up. - Handle big data sets fast. The `predict_age_batch` tool lets you process up to ten names in a single call, making large-scale data enrichment efficient. - Maintain privacy compliance. You get demographic insights without needing to collect or store sensitive birth dates or PII. - Improve prediction accuracy. By adding country scope to the `predict_age` function, you narrow down possibilities and get more reliable age estimates. - Understand the confidence level. The results include data counts, so you always know how statistically sound the predicted age is. ## How It Works The bottom line is, your AI client translates a simple name into actionable demographic data points automatically. 1. First, subscribe to this MCP and connect your preferred AI client through Vinkius. 2. Next, ask your agent to predict ages. You'll provide the name(s) and optionally include a country code for better accuracy. 3. Your agent calls the necessary tool, and you receive the estimated age and the statistical data count used for the prediction. ## Frequently Asked Questions **How does Agify predict age using `predict_age`?** It predicts the estimated age by comparing the provided first name against a vast, statistical database of demographic records. This gives you an educated estimate, not a guaranteed fact. **Can I process more than 10 names with `predict_age_batch`?** The current tool is limited to batches of up to ten first names in one request. If you have larger lists, you'll need to break the data into smaller chunks. **Does Agify require a country code for `predict_age`?** No, it doesn't, but adding a country scope significantly improves accuracy. It tells the system which regional dataset to focus on. **What is the data count metric in Agify results?** The data count shows how many records were used from the underlying database to make that specific age prediction. A higher number means a more reliable estimate. **Do I need an API key to use `predict_age`?** No, you can start testing without one. However, for high-volume or production use of `predict_age`, you must register and provide your Agify API Key in the connection settings. This key authenticates your calls and ensures stable performance when running complex data enrichment pipelines. **What happens if I pass bad names to `predict_age`?** If a name is unrecognizable, the tool returns an error specific to that input. The API doesn't fail entirely; it simply flags the problematic entries so your agent can skip them and process the rest of your list. Always validate inputs before calling `predict_age`. **Is there a rate limit I should know about when using `predict_age_batch`?** While you can process up to 10 names per call, excessive requests in quick succession may trigger throttling. If your workflow sends too many batches too fast, the system will return a 429 error code. Implement exponential backoff logic in your client when dealing with large datasets. **How does `predict_age` handle missing country codes?** If you don't scope by country, the tool uses global default data for prediction. While this works for general analysis, providing an ISO code dramatically increases accuracy and improves demographic specificity. Always try to include the country scope if your user base is regional. **Can I predict the age of multiple people at once?** Yes! Use the `predict_age_batch` tool. You can provide an array of up to 10 names in a single request to get multiple age estimations efficiently. **How can I make the age prediction more accurate for a specific region?** When using the `predict_age` tool, you can provide an optional `country_id` (ISO 3166-1 alpha-2 code). This scopes the data to that specific country, providing a more localized age estimate. **Is an API key required to use this server?** An API key is optional for low-volume testing, but recommended for production use or higher rate limits. You can obtain one at Agify.io.