Skip to main content
For AI agents: a documentation index is available at https://docs.parallel.ai/llms.txt. The full text of all docs is at https://docs.parallel.ai/llms-full.txt. You may also fetch any page as Markdown by appending .md to its URL or sending Accept: text/markdown.
Parallel offers three integration paths for developers. The right choice depends on where your agent runs, how it authenticates, and how much control you need.

​
Decision guide

Use the CLI with a plugin or Agent Skills.If your agent has terminal access — Claude Code, Cursor, Windsurf, Cline, GitHub Copilot — the CLI is the most capable integration. It exposes all Parallel APIs (search, extract, research, enrich, findall, monitor) and produces structured JSON that agents parse natively.CLI commands are also deeply embedded in LLM training data. Models already know how to compose shell commands, pipe output, and handle JSON — no schema overhead required.Why not MCP? In terminal-based agents, CLI tools consume far fewer context tokens than MCP tool schemas. An MCP server dumps its full tool catalog into the context window upfront. A CLI call like parallel-cli search "query" --json costs only the tokens for the command and its output.

​
Quick comparison

​
API coverage

​
Authentication

​
Get started

CLI + Skills

Install the CLI, authenticate, and add agent skills for your coding environment.

MCP Servers

Connect Search MCP or Task MCP to a chat assistant or your own app.

SDK / Tool Calling

Define Parallel as a native tool in your agent framework. See also: LangChain, Vercel.

​
Can I use multiple integration methods?

Yes. Many teams use CLI for local development and coding agents, MCP for chat assistants and LLM-powered apps, and the SDK for custom agent loops that need full control. They all hit the same Parallel APIs with the same API key.