Integration

Perplexity integration

AI-powered research and question answering platform with real-time web search integration. Get accurate, cited answers grounded in current internet information. Features search filtering, related question suggestions, and source attribution for building research-backed AI applications.

Connect Perplexity How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Perplexity.Built from the 6 Perplexity tools below, on the connection you add once.

Common Perplexity use cases

web research
research queries
monitor async jobs
deep research queries
discover available models
retrieve deep research results
fact checking
model selection
content extraction
check research status

What you can do with Perplexity

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Async chat, 3 operations

create_async_chat_completionCreate async chat completionPOSTSubmit an asynchronous chat completion for long-running deep research queries.
get_async_chat_completionGet async chat completionGETRetrieve the response for a specific asynchronous chat completion request by ID.
list_async_chat_completionsList async chat completionsGETList all asynchronous chat completion requests and their statuses.

Chat, 1 operation

chat_completionsChat completionsPOSTCreates chat completions with web search grounding. Get AI answers backed by real-time internet search results with citations.

Model, 1 operation

list_modelsList modelsGETList all models available through the Perplexity API.

Search, 1 operation

searchSearchPOSTPerform a web search and retrieve full extracted content from result pages.

Use Perplexity from Claude Code, Cursor or Codex

Connect Perplexity in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Perplexity operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Perplexity

Create your workspace
Sign up free. Nothing to install.
Connect Perplexity once
Add your Perplexity connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Perplexity integration FAQ

What can you do with the Perplexity integration?

LiveContext exposes 6 operations on Perplexity, covering async chat, chat, model and search. Common uses include web research, research queries and monitor async jobs.