Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the PredictHQ Events API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2FPredictHQ%2Fpredicthq" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2FPredictHQ%2Fpredicthq" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with PredictHQ Events API.
Search real-world events by keyword, location radius, and country
Filter events by category, date range, and active window
Rank results by predicted attendance and local or global rank
Page through results with limit and offset controls
Sort events by rank, relevance, or date
GET STARTED
Patterns agents use PredictHQ Events API for, with concrete tasks.
★ AI Agent Demand Signals
An AI planning agent connected through Jentic searches PredictHQ for events near a business location and reads back their predicted attendance and rank to explain expected demand spikes. The agent filters by category and date range, so a forecasting assistant can flag the concerts, sporting fixtures, and conventions likely to move footfall.
Search PredictHQ for events within 20 km of a store over the next month and return them ranked by predicted attendance
Location-Based Event Feeds
A market intelligence tool pulls upcoming events by country and location radius, filtering on category and active window so the feed reflects what is happening in each region. PredictHQ returns structured records with rank and attendance, which the tool aggregates into a demand calendar.
Retrieve active events in a country for a date range and group them by category and rank
Attendance-Ranked Alerts
A notification service watches for high-impact events entering a region by querying PredictHQ on a schedule and filtering on rank and predicted attendance. When a major event is detected the service alerts staffing or pricing systems to prepare for the demand.
Search for events above a chosen rank near a location and alert when a new one appears
1 endpoints — the predicthq events api searches real-world events and returns them ranked by predicted attendance and impact.
METHOD
PATH
DESCRIPTION
/v1/events/
Search real-world events filtered by location, category, and date, ranked by predicted attendance
/v1/events/
Search real-world events filtered by location, category, and date, ranked by predicted attendance
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the PredictHQ API by hand means registering an app, handling the bearer token, and shaping the location, category, and rank filters yourself. Through Jentic you install once, import PredictHQ from the API Directory, store the token once, and your agent calls the events search operation with structured inputs.
Permission scoping
The PredictHQ endpoint is a read-only events search, so a rule can bound your agent to just that one operation. You choose which operations it may call, so it can read ranked event data and reach nothing else in your account.
Credential isolation
Your PredictHQ bearer token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'search ranked events' or 'events near a location', and Jentic returns the matching PredictHQ operation with its input schema so the agent calls it without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using PredictHQ Events API through Jentic.
What authentication does the PredictHQ Events API use?
The PredictHQ Events API authenticates with an OAuth 2.0 bearer token per its OpenAPI spec: you pass the token in the Authorization header as a bearer credential on each request. Through Jentic the token is stored once, encrypted, by your own Jentic One instance and injected at call time, so it never enters the agent's prompt or logs.
Can I search events by location and rank with the PredictHQ API?
Yes. The events search operation accepts a location radius, country, keyword, category, and date range, and returns each event with its rank, local rank, and predicted attendance. You can sort and page the results to focus on the highest-impact events first.
Is there a PredictHQ MCP server?
You don't need an MCP server to give your agent the PredictHQ API. Jentic connects it directly from the API Directory: import PredictHQ, store your token once, and your agent calls the events search operation. Discovery happens on demand, so no extra server's tool definitions sit in the agent's context.
Can I limit what my agent is allowed to do with the PredictHQ API?
Yes. Write a rule that permits only the events search operation, so the agent can read ranked event data but reach nothing else in your PredictHQ account, and every call it makes is logged. You choose the operations it may call, so nothing beyond read access is included unless you add it.
What are the rate limits for the PredictHQ Events API?
The OpenAPI spec does not specify rate limits. Check the PredictHQ documentation at https://www.predicthq.com for current limits and quota details.
How do I search PredictHQ events through Jentic?
Import the PredictHQ API from the Jentic directory, store your bearer token once, and have your agent search with an intent such as 'ranked events near a location'. Jentic returns the events search operation with its input schema so the agent supplies the filters and reads the ranked results. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Know of an official OpenAPI document? Contribute it →
For Agents
Search PredictHQ for real-world events filtered by keyword, location, country, category, and date, returning each with predicted attendance and rank. Returns structured event data for demand forecasting, planning, and alerting.
Use for: Find major concerts in a city next month, Search for sports events ranked by expected attendance, List conferences happening in a country this quarter, Get high-impact events near a set of coordinates
Not supported: Does not sell tickets, manage attendees, or create events. Use for event data search and ranking only.
The PredictHQ Events API searches real-world events and returns them ranked by predicted attendance and impact. It exposes a single events search operation that filters by keyword, location radius, country, category, date range, and active window, and returns each event with its rank, local rank, and predicted attendance. It reads structured event data and is suited to demand forecasting, planning, and alerting rather than ticketing.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>