// Use this when you need the raw HTTP response for non-HTML content or APIs. Examples: JSON, XML, RSS/Atom, CSV, plain text, files, or downloads. If the target is a human-readable web page (HTML) that should be converted to markdown, use fetch-webpage instead.
Use this tool when you need up-to-date web search results from Exa MCP. It calls `web_search_exa` over `text/event-stream`, supports optional `exaApiKey`, and returns extracted text content from search results.
Fetch webpages into Markdown by URL, with a selectable --provider parameter for pure.md, defuddle.md, markdown.new, or r.jina.ai.
Use this tool when you need up-to-date information from the internet. It grounds the model with real-time Google Search results across languages, improving factual accuracy and enabling responses with verifiable citations beyond the model's knowledge cutoff.
Use Ollama Cloud web APIs for single-query web search and single-page web fetch. Requires OLLAMA_API_KEY and uses shell HTTP requests, preferably curl.
Generate images using the Pollinations.ai API. Supports models such as flux, zimage, imagen-4, klein, klein-large, gptimage (free), and seedream, kontext, nanobanana, gptimage-large (paid). Use when the user asks to generate, create, or draw images from text prompts.
| name | fetch-url |
| description | Use this when you need the raw HTTP response for non-HTML content or APIs. Examples: JSON, XML, RSS/Atom, CSV, plain text, files, or downloads. If the target is a human-readable web page (HTML) that should be converted to markdown, use fetch-webpage instead. |
Fetch raw HTTP responses from URLs. Supports multiple URLs and custom headers.
# Single URL
node {baseDir}/scripts/fetch.mjs "https://api.example.com/data"
# Multiple URLs
node {baseDir}/scripts/fetch.mjs '["https://api.example.com/data1", "https://api.example.com/data2"]'
# With custom headers (per-URL)
node {baseDir}/scripts/fetch.mjs '["https://api.example.com/json", "https://api.example.com/text"]' '[{"accept":"application/json"}, {"accept":"text/plain"}]'
# With timeout
node {baseDir}/scripts/fetch.mjs "https://api.example.com/data" --timeout 60000
# GitHub API - get repository info
node {baseDir}/scripts/fetch.mjs "https://api.github.com/repos/microsoft/vscode" '{"accept":"application/json","user-agent":"Mozilla/5.0"}'
# SOAP service or XML endpoint
node {baseDir}/scripts/fetch.mjs "https://api.example.com/soap" '{"accept":"application/xml"}'
# Sitemap
node {baseDir}/scripts/fetch.mjs "https://example.com/sitemap.xml"
# RSS 2.0 feed
node {baseDir}/scripts/fetch.mjs "https://example.com/rss.xml" '{"accept":"application/rss+xml"}'
# Atom feed
node {baseDir}/scripts/fetch.mjs "https://example.com/atom.xml" '{"accept":"application/atom+xml"}'
# CSV data
node {baseDir}/scripts/fetch.mjs "https://example.com/data.csv" '{"accept":"text/csv"}'
# Plain text
node {baseDir}/scripts/fetch.mjs "https://example.com/robots.txt" '{"accept":"text/plain"}'
# Fetch JSON and XML in parallel
node {baseDir}/scripts/fetch.mjs '["https://api.example.com/data.json", "https://api.example.com/data.xml"]' '[{"accept":"application/json"}, {"accept":"application/xml"}]'
urls_json: JSON array of URLs or a single URL stringheaders_json: Optional JSON array of headers objects (same length as urls)--timeout <ms>: Request timeout in milliseconds (default: 30000)Notes: