Does the Perplexity node return live web results with sources?

Yes. The Search the Web operation and the grounded chat completions query current web data and return answers with citations, so you get fresh information rather than a model's stale training data. You can drop the answer and its sources into any downstream node.

How do I connect Perplexity to NoClick?

Authenticate with a Perplexity Sonar API key, which you paste into the node's credential field. The node also exposes Generate Auth Token and Revoke Auth Token operations for managing tokens programmatically once you are connected.

Can a workflow react to an event and run a Perplexity search on its own?

The Perplexity node is request and response, so it does not fire on its own. Wire it to any trigger in NoClick, such as a schedule, a form submission, or an inbound message, and that event will kick off the search or chat completion automatically.

Can it return structured data instead of a paragraph of text?

Yes. The Structured JSON Output operation makes the model answer as a defined JSON object rather than prose, so fields like category, sentiment, or extracted values come back ready to route or store. That makes it clean to chain into later nodes without parsing free text.

What are the async chat completion operations for?

They handle long-running or heavy requests without blocking a workflow. Fire Create Async Chat Completion to start the job, then use Get Async Chat Completion to fetch the result later or List Async Chat Completions to see what is in flight.

What makes OpenCode different here?

OpenCode is open and model-agnostic, so you have flexibility over the underlying model. NoClick handles running it and connecting your apps as tools.

How do I give OpenCode tools?

Connect an integration node to the agent's tools handle and choose the operations to allow. Each becomes a tool the agent can call.

Do I manage any infrastructure?

No. NoClick runs the OpenCode harness in a hosted sandbox and resolves credentials for the apps you connect.

Can it combine several apps?

Yes. Add as many integrations as you need and the agent can use them together in one run.

Connect OpenCode to Perplexity

Give an AI agent Perplexity as a tool and it can look things up for itself instead of guessing. It can search the web, run cited chat completions, pull academic papers, and search SEC filings mid-task, then feed the answers straight back into whatever it is working on. When it needs a clean object rather than prose it can request structured JSON output, and it can generate embeddings to compare or rank text.

Loading preview…

Opens a workflow with 15 tools ready to use.

What happens next

Set up in minutes

The open button drops you into a guided setup. It asks exactly this, nothing else:

Choose where it runs
On your computer through your own OpenCode, or hosted in the cloud. The rest of setup adapts to your choice:
Pick what it can do in Perplexity
A preset of real Perplexity operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect Perplexity
One sign-in. The agent acts through your account, scoped to the operations you picked.
Add your personal MCP link
The last step mints a private MCP URL for this agent and walks you through exactly this, with your real link filled in. The page flips to Connected the moment your OpenCode first calls in. opencode mcp add only saves the config. OpenCode connects when it starts — run opencode, or restart a running one.
1. Run this in your terminal
$opencode mcp add
2. Choose Remote and paste your server URL
https://mcp.noclick.app/s/<your-link>
3. Choose No when asked about OAuth authentication — the link itself is the key
<your-link> is your personal server URL — setup mints it for you.

Exact capabilities

Tools OpenCode gets

Pick the operations you want and each becomes a tool the agent can call directly while it works.

Perplexity

15 tools

Create Chat Completion

Generate a search-grounded model answer for a chat conversation.

Create Async Chat Completion

Submit a long-running (e.g. deep-research) completion as a background job.

List Async Chat Completions

List all async chat-completion jobs for the account.

Get Async Chat Completion

Poll the status and retrieve a specific async completion job.

Search the Web

Get raw, ranked web search results (title, URL, snippet).

Create Agent Response

Run a frontier model with Perplexity web-search tools and filters.

Create Embeddings

Generate vector embeddings for text.

Create Contextualized Embeddings

Generate context-aware embeddings (document + surrounding context).

List Models

List the models available to the account.

Generate Auth Token

Programmatically create a new API key/token for the account.

Revoke Auth Token

Revoke an existing API key/token (rotation).

Computer Usage Analytics

Retrieve account usage/analytics data.

Academic Search (Chat)

Chat completion grounded in scholarly sources (search_mode: academic).

SEC Filings Search (Chat)

Chat completion grounded in SEC filings (search_mode: sec).

Structured JSON Output (Chat)

Chat completion with a JSON schema response_format for validated output.

Starting points

What you can build

When a new lead lands in your CRM, ask Perplexity to research the company from live web results and write a short briefing before your team follows up.

Every morning, run a web search for news about your competitors and post a cited summary to Slack.

Pass an incoming support ticket through a chat completion with structured JSON output so the reply comes back as tagged fields you can route on.

On a schedule, run an SEC filings search for a ticker and flag any new risk-factor language in a report.

Turn a research question into an academic search, then summarize the top papers into a digest for the team.

Create embeddings for each incoming document so a downstream node can match it against your existing knowledge base.

Meet the runner

About OpenCode

OpenCode is an open, model-agnostic command-line coding agent. In NoClick it runs hosted and gains your apps as tools, so it can act on real systems rather than just edit files. Wire an integration into the agent and OpenCode can use that app’s operations directly while it works. It is a flexible choice when you want an open agent with broad model support and real tool access.

Open and model-agnostic

Flexible across many underlying models

Good general-purpose tool use

Lightweight to point at a focused task

Good to know