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.For Search and Extract, use /v1/search and /v1/extract for all new integrations and agent tool calls. Use /v1beta/search and /v1beta/extract only when maintaining an existing integration that already uses them. The request bodies changed too: on /v1/extract, full_content, fetch_policy and excerpt_settings go inside advanced_settings, and sending the v1beta top-level excerpts, full_content and fetch_policy to /v1/extract returns a 422. On /v1/search, search_queries is required (at least one short keyword query), and max_results, source_policy and fetch_policy go inside advanced_settings; sending only objective, or sending those fields at the top level, returns a 422. Do not substitute /v1 for the documented FindAll or Ingest endpoint paths.If you are evaluating Parallel Search or comparing it with other search APIs, read How to Eval Parallel Search before you build the harness, especially its Common pitfalls section. The most common mistake is sending the raw question as both objective and the only entry in search_queries. Write a goal-style objective and 1-3 short keyword queries instead.
The Parallel plugin for Claude Code gives your coding agent access to live web search, content extraction, deep research, and data enrichment — all available as slash commands and automatic skills directly inside Claude Code.
View the complete repository for this plugin here

Features

  • Web Search: Fast, real-time search for current events, documentation lookups, and fact-checking
  • Content Extraction: Clean content extraction from web pages, including JavaScript-heavy sites, and PDFs
  • Deep Research: Exhaustive, multi-source research reports with configurable depth and processing power
  • Data Enrichment: Bulk enrichment of companies, people, or products with web-sourced fields like CEO names, funding, and contact info

Prerequisites

The plugin bundles Parallel’s hosted MCP server (parallel-search), whose web_search, web_fetch, and web_decisions tools work without the CLI, an API key, or a Parallel account, subject to anonymous usage limits. Its web_research tool requires signing in with a Parallel account that has a usable credit balance. After sign-in, authenticated MCP calls are billed to your Parallel account at the same rates as the underlying API, after any free usage your account includes. The CLI-backed skills—including the search and extraction slash commands below, deep research, enrichment, FindAll, and monitoring—require the CLI to be installed and authenticated with a funded Parallel account.
1

Install the Parallel CLI

Install the Parallel CLI via pipx:
See the CLI docs for uv, Homebrew, npm, and other installation methods.
2

Authenticate

See the CLI docs for other authentication methods.

Installation

Install the plugin from the Claude Code Plugin Marketplace:
Restart Claude Code after installation. For CLI-backed skills, then run the setup command to verify the CLI is installed and authenticated:

Slash Commands

Once installed, the following commands are available in Claude Code:

Usage

Beyond slash commands, the plugin also installs skills that Claude Code uses automatically based on context:
  • Ask a question that needs current information and Claude will search the web
  • Paste a URL and ask Claude to read it — it will extract the content
  • Ask for exhaustive research on a topic and Claude will run a deep research task
  • Give Claude a list of companies and ask it to find their CEOs — it will use data enrichment

Learn More

For detailed documentation, skill definitions, and contribution guidelines, see the parallel-agent-skills repository on GitHub. For Agent Skills support with other coding agents (Cursor, Cline, Copilot, etc.), see the Agent Skills integration.