--- title: "Peekalink Integration" description: "Connect over an API key to turn any URL into structured link-preview metadata, including titles, descriptions, images, favicons, and platform-specific details for recognized services." url: https://flowrunner.ai/integrations/peekalink date_modified: 2026-08-07T17:20:23-07:00 --- # Peekalink [Utilities & Personal](https://flowrunner.ai/integrations/category/utilities-personal) Connect over an API key to turn any URL into structured link-preview metadata, including titles, descriptions, images, favicons, and platform-specific details for recognized services. [Verified](https://flowrunner.ai/integrations/verified "What does verified mean?") · 2 actions · API key · available [Peekalink website](https://www.peekalink.io/) · [Platform Documentation](https://www.peekalink.io/documentation) · Capability data verified 2026-07-14 1. A user-submitted URL arrives for enrichment 2. Agent calls Check Availability to confirm the URL can be previewed 3. Agent calls Preview Link to fetch title, description, image, and details 4. Agent reads the core metadata and any service-specific fields 5. Agent confirms the title and image are present and sensible 6. Agent posts the enriched preview for review 7. A person approves the preview before it appears on public material ## What This Integration Enables The Peekalink connector gives agents two focused read actions. Preview Link generates a rich preview for a URL, returning the title, description, domain, type, a main image, and a favicon, plus a type-specific details object for recognized services with data such as video, author, or product information. Check Availability confirms whether a URL can be previewed at all, returning a single boolean without spending a full preview, which makes it an inexpensive filter for a batch of links. Both actions read; nothing writes. The connector supplies the enrichment; the surrounding flow decides what to store and what to publish. ### Without FlowRunner **Links stored raw**: Only the bare URL is saved, with no title or image **Dead links slip in**: Unpreviewable URLs get stored and surface as broken cards later **Previews built by hand**: Someone copies a title and grabs an image for each shared link ### With FlowRunner **Links stored enriched**: The agent attaches title, description, and image on the way in **Dead links filtered**: Check Availability screens out URLs that will not resolve **Previews built in the flow**: Preview Link assembles the card automatically for review ## Use Case Scenarios ### URL Enrichment on Intake When a user submits a URL, the agent calls Preview Link to fetch the title, description, and preview image, then stores the enriched record rather than the bare link. Later views show a proper card instead of a naked address, and the enrichment happens without anyone assembling it by hand. ### Batch Pre-Validation Given a list of URLs, the agent runs Check Availability across the batch to filter out links that cannot be previewed, then calls Preview Link only on the ones that will resolve. The pre-check saves requests and keeps unpreviewable links out of the downstream store. ### Preview Card for Sharing Before a link is shared to a channel or a content feed, the agent calls Preview Link to build a rich card with title, description, and image. It posts the card for review so the shared link carries context, and a person confirms it before it goes out. ## Human-in-Loop Highlight Fetching a preview is a safe read, and the connector only reads; it never publishes anything on its own. The judgment lies downstream, because a preview that lands on public material, a shared card, a content feed, an outbound message, becomes the face of that link to everyone who sees it. This is [human-in-the-loop](https://flowrunner.ai/concepts/human-in-the-loop) at the boundary between enriching a link and publishing it: when a fetched preview would appear on public material, the agent pauses and routes the assembled card to a person through their preferred channel. The message is specific: "This link previews as a pricing-page title with last quarter's hero image. Publish the card as fetched, or fix it first?" The agent gathers the metadata; a person owns the preview the outside world reads. Agent processes routinely Detects exception requiring judgment Clear match Continues automatically Ambiguous Routes to human via preferred channel Human decides Agent resumes with decision ## Agent Capabilities 2 actions ### Link Preview 2 - **Preview Link** Generate a rich preview for a single URL, returning title, description, domain, type, a main image, and a favicon. For recognized services a type-specific details object adds platform data such as video, author, or product information. - **Check Availability** Check whether Peekalink can generate a preview for a URL without generating the full preview, returning a single boolean. Useful as an inexpensive pre-check or to filter a batch of URLs. ## Frequently Asked Questions ### What can FlowRunner do with Peekalink? FlowRunner agents can run Preview Link and Check Availability in Peekalink. ### Does connecting Peekalink to FlowRunner require OAuth? No. Peekalink connects to FlowRunner with an API key, no OAuth flow required. ### Can Peekalink trigger a FlowRunner workflow automatically? Peekalink doesn't currently expose triggers in FlowRunner. It connects as an action step inside workflows started by another trigger. **Work at Peekalink?** This integration exposes Peekalink to AI agents on every FlowRunner plan, including through MCP, at no cost to you. [See what FlowRunner offers integration partners](https://flowrunner.ai/integrations/partners), including how to keep this page current. --- Markdown version of https://flowrunner.ai/integrations/peekalink. Site index: https://flowrunner.ai/llms.txt