Explore
MCP servers and skills: search, filter by where they run, and compare.
agentfetch-mcpbch1212
LocalMCP server for fetching web URLs with token estimation, caching, and intelligent routing. Built for AI agents.
PythonMIT★ 3Few starsNo key
MCP servers and skills: search, filter by where they run, and compare.
MCP server for fetching web URLs with token estimation, caching, and intelligent routing. Built for AI agents.
PythonMIT★ 3Few starsNo key
A smart web search & fetch MCP server with built-in caching, rate-limiting, and content extraction. Zero API keys required.
PythonMIT★ 1Few starsNo key
LLM-powered MCP server for building financial deep-research agents, integrating web search, Crawl4AI scraping, and entity extraction into composable analysis flows.
PythonApache-2.0★ 26No key
Drive the real, logged-in Chrome you already have open — cross-platform, token-optimized, and Ubuntu headless 24/7.
PythonMIT★ 5No key
PythonMIT★ 1Few starsNo key
Jiro Search: Open-source, self-hosted search API with 9 engines, 12 social scrapers, MCP server, hybrid search & AI synthesis. Free SerpAPI alternative. MIT licensed. pip install jirosearch
PythonMIT★ 4Few starsNo key
An MCP which helps accessing the browser and saving credits of any AI tool in use
PythonMIT★ 1Few starsNo key
A Model Context Protocol server that provides documentation access capabilities. This server enables LLMs to search and retrieve content from documentation websites by scraping them with crawl4ai. Bui
PythonMIT★ 18No key
Headless Skill Hub and GitOps for Agentic Memory. Turn complex codebases and documents into version-controlled, immutable cognitive skills. Featuring AST chunking, cryptographic Delta Updates, and nat
PythonApache-2.0★ 5No key
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, Codex, Grok, Cu
PythonMIT★ 5Needs a key
Web research toolkit for LLM agents: search, fetch, extract, answer, map. MCP server + CLI + daemon, with anti-bot escalation and caching.
PythonAGPL-3.0Few starsNo key
AI-Powered Automated Newspaper Generation Tool with Claude Code Skills support
SkillMIT★ 2Few starsNo key
⚡ Stop wasting hours on email QA. Drop in a Jinja2 template, automatically mock real-world data, and preview every conditional branch in your Gmail inbox in 5 seconds flat.
PythonMIT★ 1Few starsNo key
Token-efficient browser agent for local LLMs — Playwright + accessibility tree + MarkGrab, MCP native.
PythonMIT★ 9No key
This repository provides a Model Context Protocol (MCP) server that retrieves the raw HTML content from a given URL to provide context to Large Language Models (LLMs). It acts as a tool for LLMs to fe
PythonUnlicense★ 1Few starsNo key
kairos picks the right LLM technique for any task by querying a curated wiki of agent patterns - RAG, ReAct, Reflexion, and 17 more. Karpathy LLM Wiki + rule-based selector + 3 working runners. Zero A
PythonMITFew starsNo key
A local MCP server aggregating 15 web search & extraction tools across 5 providers (Jina, Tavily, Exa, Firecrawl, Bocha)
PythonMITFew starsNo key
Production-style MCP server for AI agents: incremental web scraping, typed SQLite cache, FastMCP tools/resources, and offline parser tests.
PythonMITFew starsNo key
Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at 66% lower cost and up to 88% fewer tokens, plus a precision-
PythonMIT★ 60No key
Who stands behind it
