Reliable web tools for Pi: search for sources, fetch over HTTP, and use headless browsing only when explicitly requested.

一个轻量的ai websearch的自建个人方案，支持baidu/tavily api, bing 和学术搜索引擎 ，内置sqlite 缓存和llm 摘要能力，支持litellm claude websearch 扩展接入

Token-lean web microfetch for LLM agents: any URL → clean markdown via CLI, MCP server, and Claude Code plugin. Real browser-cookie auth, passkeys, anti-bot reach, on-by-default prompt-injection defense, plus on-device multimodal ASR/OCR. A single Rust binary — not a browser.

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.

Easyai - run local models with your tools, easy tools def, buildin RAG, fs tools, web search and fetch, MCP server and ai client with local tools all made simple and easy

MCP server for Ollama web search and web fetch APIs. Enables AI assistants like Claude Desktop to search the web and fetch webpage content.

Markdown-first web retrieval skill for AI agents (Cloudflare + Jina + Firecrawl)

🐟 TinyFish MCP server: Multi-key pooling to bypass rate limits + Context-efficient toolset for AI agents (Claude Code, Cursor).

MCP server for fetching web URLs with token estimation, caching, and intelligent routing. Built for AI agents.

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 web search and page fetching with markdown conversion for AI model integration in applications and citations.

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.

Pi coding-agent extension showcase with MCP tool loading, exact-URL web fetch, policy-based security guardrails, compact TUI renderers, and managed setup workflow.

MCP server for AI agents: high-fidelity web search (Exa) + tiered web fetch (Exa→browser→Firecrawl) with SSRF guard. Drop-in replacement for built-in WebSearch/WebFetch in Claude Code, Cursor & Claude Desktop.

Unified client signal layer — parse structured data from HTTP requests: IP, user agent browser and OS, bot detection, language and locale, cookies, etc.

a multi-step web research agent over the web, Wikipedia, and arXiv - built with LangGraph + LCEL, streams each step in real-time, and grounds every report in sources it actually fetches and reads.

Omni-Search-Skill: a full-stack web search and retrieval skill for fast, no-blind-spot search, fetch, and crawl workflows.