Perigon provides an HTTP REST API for retrieving news and web content data, offering structured data suitable for various applications.
Perigon provides an HTTP REST API for retrieving news and web content data, offering structured data suitable for various applications. On Nagent, Perigon is exposed as a fully-configurable news & lifestyle integration that any agent can call — 9 actions, and API key authentication. No code is required to wire Perigon into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Perigon to automate the kinds of tasks news & lifestyle teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Perigon into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Perigon, with input parameters and output schema. Drop these into any step of an agent built in Helix.
PERIGON_GET_ARTICLESTool to retrieve a list of news articles based on filters. Use when keywords, sources, or date ranges are specified.
Input parameters
Search query term or phrase
Newest date for articles (YYYY-MM-DD or ISO8601)
Oldest date for articles (YYYY-MM-DD or ISO8601)
Page number (1-indexed)
Order to sort articles
2-letter country code to filter news sources
Comma-separated list of domain names to include
Comma-separated list of source IDs
Article category, e.g., technology, sports
2-letter language code, e.g., 'en'
Number of results per page (1-100)
Comma-separated list of domain names to exclude
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PERIGON_GET_COMPANIESTool to retrieve information on companies in Perigon’s entity database. Use when you need a full list of companies. Use after confirming a valid API key is present.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PERIGON_GET_JOURNALISTSTool to retrieve journalist profiles including title, Twitter handle, bio, and location. Use when you need detailed journalist info to enrich content with author metadata.
Input parameters
Number of items to return (default: 10, max: 100)
Search string for journalist name
Number of items to skip for pagination
Filter journalists by outlet name
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PERIGON_GET_SOURCESTool to retrieve a list of media sources with filtering options. Use when you need to list sources by domain, country, category, or traffic metrics.
Input parameters
Page number for pagination (default: 1)
Filter by domain of the source (e.g., cnn.com)
Filter by country code (ISO-3166-1 alpha-2, e.g., US)
Filter by category of the source
Filter by language code (ISO-639-1, e.g., en)
Results per page (default: 10, max: 100)
Filter for sources with maximum stories per month
Filter for sources with a maximum SimilarWeb global rank
Filter for sources with minimum stories per month
Filter for sources with a minimum SimilarWeb global rank
Comma-separated list of domains to exclude
Comma-separated list of domains to include
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PERIGON_GET_STORIESTool to retrieve clusters of related articles covering the same event or topic with aggregate metrics. Use when you need to fetch filtered and sorted story clusters after configuring query parameters.
Input parameters
Search query keywords or phrases
Comma-separated story IDs
Page number for pagination
Story type, e.g., 'story', 'opinion', 'analysis'
Only stories with images
Only stories with videos
Comma-separated domains to filter by
Sort method for story results (default: createdAt)
Only show stories in a given cluster
Country code, e.g., 'us'
Exclude comma-separated story IDs
Only paywalled or non-paywalled content
Comma-separated source IDs to filter by
End date for filtering stories in ISO 8601 format
News category, e.g., 'sports'
Language code, e.g., 'en'
Start date for filtering stories in ISO 8601 format
Maximum Perigon story score
Minimum Perigon story score
Filter by sentiment
Minimum clustering score
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PERIGON_GET_TOPICSTool to retrieve all available Perigon news topics. Returns a list of topics that can be used to filter articles or stories. Each topic includes an ID, name, and labels (category/subcategory).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PERIGON_GET_WIKIPEDIATool to search and filter Wikipedia pages. Use when you have a search query ready and want to retrieve relevant Wikipedia articles.
Input parameters
Search query for the Wikipedia articles
Page number for pagination (default: 1)
Number of results per page (default: 10, maximum: 100)
Two-letter Wikipedia language code (e.g., 'en', 'es')
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PERIGON_VECTOR_SEARCH_ARTICLESTool to perform a vector search on Perigon’s real-time news database. Use when you need to retrieve semantically similar news articles given a natural language query.
Input parameters
Natural language search text to vectorize and find similar articles
Number of top results to return, must be >=1
Optional filters to narrow down results (source, category, language)
Advanced vector search options like model override
Whether to include article vectors in response
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PERIGON_VECTOR_SEARCH_WIKIPEDIATool to perform semantic retrieval of Wikipedia pages using vector search. Use after obtaining a search query to find relevant Wikipedia articles.
Input parameters
Maximum number of results to return (default: 10)
Search query for Wikipedia pages
Whether to include context passages in the response
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 98 agents privately built on Nagent that already use Perigon.
Build on Nagent
Connect Perigon to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Perigon, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Perigon is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Perigon is connected, you configure its 9 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Perigon steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Perigon event fires, the agent kicks off automatically.
Every Perigon action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Perigon ships with 9 pre-built news & lifestyle actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Perigon together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Perigon-based workflows tailored to your business.