Agent Native

exa-fetch

This skill fetches and extracts the full text content from webpages using the Exa web fetch tool, converting pages into clean markdown format.

by ExaOfficial publisherNot reviewed

Identity proven by GitHub's verified organisation badge (exa-labs)

Agents
Claude Code
License
MIT (permissive)
Pin
0c6bb4cpinned Oct 9, 2026
Context cost
about 470 tokenswhen the skill loads
GitHub stars
9on exa-labs/exa-cursor-plugin
Scripts
None found

What it does

“Read a webpage's full content using Exa. Gets clean markdown text from any URL. Use when you have a specific URL and need its contents. Supports batching multiple URLs. Use exa-web-search instead when you need to find pages first.”
The author's description, from SKILL.md

Generated summary from the skill's own text

This skill fetches and extracts the full text content from webpages using the Exa web fetch tool, converting pages into clean markdown format. It's designed for situations where you already have a specific URL and need to read its contents, supporting batch fetching of multiple URLs at once with configurable character limits.

When to use it

  • You have a specific URL and need to read its full content
  • Extracting data or information from a known webpage
  • Following up on search results to get complete page text
  • Reading documentation, articles, or blog posts at specific URLs

When not to

  • You need to find and search for pages first, use web search instead
  • The Exa MCP server is not installed or connected to the agent

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add exa-labs/exa-cursor-plugin --skill exa-fetch

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install exa-labs/exa-cursor-plugin exa-fetch@0c6bb4c04067971681f5777606acb60a71ed7270

Installs the commit we checked (0c6bb4c).

Copy by hand

Download the folder at 0c6bb4c and put it in .claude/skills/exa-fetch for Claude Code and in .agents/skills/exa-fetch for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at 0c6bb4c

Claude Code plugin

/plugin install exa@claude-plugins-official

The publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "exa-fetch" by Exa.

Source, pinned to commit 0c6bb4c04067971681f5777606acb60a71ed7270:
https://github.com/exa-labs/exa-cursor-plugin/tree/0c6bb4c04067971681f5777606acb60a71ed7270/skills/exa-fetch

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/exa-fetch/ for Claude Code and .agents/skills/exa-fetch/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/exa/exa-fetch

SKILL.md at the pin

---
name: exa-fetch
description: "Read a webpage's full content using Exa. Gets clean markdown text from any URL. Use when you have a specific URL and need its contents. Supports batching multiple URLs. Use exa-web-search instead when you need to find pages first."
allowed-tools: mcp(exa:web_fetch_exa)
---

# Fetch URL (Exa)

Extract content from: $ARGUMENTS

## Tool

Use `web_fetch_exa` to get the full text of a webpage.

## When to Use

- You have a specific URL and need its contents
- Reading documentation pages, blog posts, or articles
- Extracting data from a known webpage
- Following up on a search result to get full content

Trigger phrases: "read this page", "fetch this URL", "extract content from", "get the page at", "what does this link say", or when a user shares a URL.

Use `web_search_exa` instead when you don't have a URL and need to find pages first.

## How to Fetch

`web_fetch_exa` accepts:
- `urls` (array of strings, required) — the URLs to extract content from
- `maxCharacters` (number, optional) — max characters to return per page (default: 3000)

### Character Limits

- Quick summary → `maxCharacters: 1000-2000`
- Standard read → `maxCharacters: 3000` (default)
- Full page content → `maxCharacters: 5000-10000`

### Batching

You can fetch multiple URLs in a single call:

```
web_fetch_exa({
  "urls": ["https://example.com/page1", "https://example.com/page2"],
  "maxCharacters": 3000
})
```

## Output Format

1. Present the key information from the page
2. If the user asked a specific question, answer it using the page content
3. Include the source URL

## Before You Start

Check if Exa MCP is installed by confirming `web_fetch_exa` is available in your tool list.

## If the MCP Server Is Not Connected

### You (the AI) must:

1. **Stop immediately** — do NOT try to fetch the URL yourself, do NOT use websearch, and do NOT try to answer from your own knowledge.
2. Inform the user that Exa MCP is not connected.

### Request the user to:

1. Run the `/exa-setup` command in Cursor to add the Exa MCP server.
2. Go to **Cursor Settings → Tools & MCP** and make sure Exa is toggled **on** (green).
3. Retry their fetch after completing the above steps.

From exa-labs/exa-cursor-plugin at 0c6bb4c, shown as plain text under its license: MIT (permissive). The license text is in LICENSE.

View SKILL.md on GitHub at 0c6bb4c

Files

1 file, 2.2 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at 0c6bb4c
All 11 skills from Exa

More from Exa

  • Exa Agent

    Exa Agent enables multi-step web research and list-building tasks by orchestrating searches and integrating premium data providers like Similarweb, financial…

    Claude Code, Codex, Cursor +4 · about 2.3K tokens · pinned 6 days ago

  • search

    This skill coordinates deep research using Exa search by analyzing query complexity, dispatching parallel subagents to search with domain-specific patterns…

    Claude Code · about 3.5K tokens · pinned 6 days ago

  • build-with-exa

    Build applications and agents using Exa's web search and content extraction APIs.

    Claude Code, Codex, Cursor +4 · about 3K tokens · pinned 6 days ago

  • company-research

    The skill enables agents to research companies using Exa's search and AI capabilities.

    Claude Code · about 1.4K tokens · pinned 6 days ago

  • exa-contents

    This skill extracts content from known URLs using Exa's /contents endpoint via HTTP POST requests.

    Claude Code, Codex, Cursor +4 · about 2.1K tokens · pinned 6 days ago

  • exa-search

    This skill enables agents to call the Exa Search API directly via HTTP POST for semantic web retrieval without an SDK.

    Claude Code, Codex, Cursor +4 · about 3.3K tokens · pinned 6 days ago

All Productivity skills
  • agent-mail-automation

    This skill enables agents to automate email operations through Composio's Agent Mail toolkit via the Rube MCP server.

    by ComposioOfficial publisher

    Claude Code, Codex, Cursor +3 · about 700 tokens · pinned 6 days ago

  • figma-use-figjam

    This skill enables agents to programmatically create and edit FigJam boards using the Figma plugin API via the use_figma MCP tool.

    by FigmaOfficial publisher

    Claude Code · about 1.7K tokens · pinned 6 days ago

  • figma-use-figjam

    This skill guides agents in using Figma's MCP tool for FigJam boards, which are collaboration canvases at figma.com/board URLs.

    by FigmaOfficial publisher

    Claude Code · about 1.7K tokens · pinned 6 days ago

  • linear

    This skill manages Linear issues by allowing agents to create tickets, update existing issues, add comments, change workflow states, and assign work through…

    by SentryOfficial publisher

    Claude Code, Codex, Cursor +4 · about 1.7K tokens · pinned 6 days ago

  • you-web

    This skill searches the live web using You.com and reads full page content to find current information beyond training data, such as API docs, release notes…

    by You.comOfficial publisher

    Claude Code, Codex, Cursor +4 · about 1.1K tokens · pinned 6 days ago

  • show-airtable-link

    This skill generates clickable Airtable links after agent actions that create, read, or modify Airtable records, tables, bases, or interface pages.

    by AirtableOfficial publisher

    Claude Code, Codex, Cursor +4 · about 1.3K tokens · pinned 6 days ago

Open roles at Exa

2 open roles on the jobs board

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use