Reliable web tools for Pi: search for sources, fetch over HTTP, and use headless browsing only when explicitly requested.
-
Updated
May 8, 2026 - TypeScript
Reliable web tools for Pi: search for sources, fetch over HTTP, and use headless browsing only when explicitly requested.
Agent skill that fetches web pages as clean markdown via markdown.new — with prompt injection protection. 82-94% token savings.
Fetch web pages as clean Markdown for AI-agent workflows.
Web research tools for Pi agents that don't trash the context window. Retrieves via Exa + Context7, stores raw payloads out-of-band, returns short source-cited briefs through a distillation firewall.
Markdown-first web retrieval skill for AI agents (Cloudflare + Jina + Firecrawl)
MCP server for fetching web URLs with token estimation, caching, and intelligent routing. Built for AI agents.
web_search and web_fetch tools for the pi coding agent. Same Anthropic OAuth bearer and server-side tools Claude Code uses, with the knobs Claude Code locks down exposed as per-call parameters.
🐟 TinyFish MCP server: Multi-key pooling to bypass rate limits + Context-efficient toolset for AI agents (Claude Code, Cursor).
Omni-Search-Skill: a full-stack web search and retrieval skill for fast, no-blind-spot search, fetch, and crawl workflows.
An agent skill about fetch WeChat public account articles (微信公众号文章) from mp.weixin.qq.com URLs and extracts title, author, account name, publish date, and full article body as clean markdown.
MCP server for Ollama web search and web fetch APIs. Enables AI assistants like Claude Desktop to search the web and fetch webpage content.
A web content fetcher MCP server that converts HTML to clean, AI and human readable markdown.
Anthropic native web fetch policy extension for the pi coding agent. Ensures native web_fetch tools are present on anthropic-messages payloads and appends web fetch guidance to the system prompt.
Convert public URLs to clean Markdown using selectable methods for versatile output modes and improved content accuracy.
Add a description, image, and links to the web-fetch topic page so that developers can more easily learn about it.
To associate your repository with the web-fetch topic, visit your repo's landing page and select "manage topics."