Matt Harris cdc1783f92 parallel-develop: simplify MCP recipe to URL-first install
Most MCP clients (Claude Code, Claude Desktop Connectors UI, Cursor,
VS Code, Windsurf, Cline) just need the URL — OAuth handles auth on
first use. Previous recipe led with the mcp-remote stdio bridge +
inline API key + Claude Desktop shell-env gotchas, which only apply to
older clients without remote-HTTP support.

Now:
- URL-first, one config block per client, tiny snippets
- mcp-remote bridge demoted to a 'Stdio fallback' section at the bottom
- Per-client quirks captured in one line each (Windsurf uses serverUrl,
  Cline needs type=streamableHttp, VS Code wraps in mcp.servers)
- Points at docs.parallel.ai/integrations/mcp/search-mcp for any client
  not listed.
2026-04-21 14:54:52 -04:00
2026-02-06 14:45:24 -05:00
2026-02-06 14:45:24 -05:00
2026-02-06 14:45:24 -05:00
2026-02-06 14:45:24 -05:00

Parallel Agent Skills

Agent Skills for Parallel — web search, content extraction, deep research, and data enrichment for AI coding agents.

Prerequisites

  1. Install the CLI

    curl -fsSL https://parallel.ai/install.sh | bash
    
  2. Get an API key at parallel.ai and set it as an environment variable:

    export PARALLEL_API_KEY="your-key"
    

    Or authenticate interactively after installing the CLI:

    parallel-cli login
    
  3. Install the skills into your AI agent (see below).

Installation

Agent Skills

Use the Vercel Skills CLI to install skills into Cursor, Cline, GitHub Copilot, and 30+ other agents.

# Install all skills globally (available in all projects)
npx skills add parallel-web/parallel-agent-skills --all --global

# Or install to current project only
npx skills add parallel-web/parallel-agent-skills --all

# Install a specific skill
npx skills add parallel-web/parallel-agent-skills --skill parallel-web-search

# Preview available skills
npx skills add parallel-web/parallel-agent-skills --list

Claude Code

Available as a Claude Code Plugin Marketplace.

/plugin marketplace add parallel-web/parallel-agent-skills
/plugin install parallel
# restart Claude Code before continuing!

# this will install the CLI and authenticate if not done already
/parallel:setup

OpenAI Codex

Install skills using the built-in skill installer (run inside Codex):

$skill-installer parallel-web/parallel-agent-skills

Then install the CLI and authenticate:

curl -fsSL https://parallel.ai/install.sh | bash
parallel-cli login

Skills

Skills follow the Agent Skills specification and double as Claude Code slash commands.

Skill Description
parallel-web-search Web search (default for most research queries)
parallel-web-extract Extract content from URLs, articles, PDFs
parallel-deep-research Comprehensive research and analysis
parallel-data-enrichment Enrich lists of companies, people, products
parallel-develop Bootstrap a Parallel API integration in your codebase (Python / TypeScript / cURL / MCP)
setup Install CLI and authenticate
status Check running research task status
result Get completed research task result

Examples

/parallel:parallel-web-search latest React 19 features
/parallel:parallel-web-extract https://docs.parallel.ai
/parallel:parallel-deep-research competitive landscape of AI code assistants
/parallel:parallel-data-enrichment Apple, Microsoft, Google - get CEO names
/parallel:parallel-develop add a research agent to my Next.js app in typescript
/parallel:setup

Resources

Local Development

Claude Code:

git clone https://github.com/parallel-web/parallel-agent-skills.git
claude --plugin-dir /path/to/parallel-agent-skills
/parallel:setup

Codex:

git clone https://github.com/parallel-web/parallel-agent-skills.git
cd parallel-agent-skills
codex
# Skills are auto-discovered via .agents/skills/

Releasing a New Version

Claude Code plugins are pinned to commit SHAs, and npx skills add pulls the latest from main.

  1. Bump the version in all three locations:
    • .claude-plugin/plugin.jsonversion
    • .claude-plugin/marketplace.jsonmetadata.version
    • .claude-plugin/marketplace.jsonplugins[0].version
  2. Commit and push to main

License

MIT

S
Description
parallel-deep-research: ONLY use when user explicitly says 'deep research', 'exhaustive', 'comprehensive report', or 'thorough investigation'. Slower and more expensive than…; parallel-web-search: DEFAULT for all research and web queries. Use for any lookup, research, investigation, or question needing current info. Fast and cost-effective. Only use…; parallel-web-extract: URL content extraction. Use for fetching any URL - webpages, articles, PDFs, JavaScript-heavy sites. Token-efficient: runs…
Readme MIT 494 KiB
Languages
Python 62.2%
TypeScript 26%
JavaScript 11.2%
Nix 0.6%