wigolo
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
Wigolo is a local-first MCP server that equips AI agents with comprehensive web intelligence capabilities including search, fetch, crawl, extract, cache, and research tools. It runs entirely on your machine with no API keys required for core features, using on-device models for ranking and embeddings to deliver zero-cost web queries. The server integrates with popular coding agents like Claude Code, Cursor, and Windsurf, as well as agent frameworks like LangChain and CrewAI. It offers ten specialized tools that return structured, cited results with explainable scoring, while keeping all data local in ~/.wigolo/.
Key Features
Use Cases
- 01Enabling coding agents to search documentation and fetch live web content during development
- 02Building AI research assistants that gather, synthesize, and cite sources autonomously
- 03Extracting structured data from websites for analysis without per-query API costs
- 04Creating self-hosted agent workflows with local web intelligence and no cloud dependencies
- 05Integrating web search and crawling into LangChain or CrewAI agent pipelines
- 06Monitoring website changes with diff detection and webhook notifications
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
wigolo — FAQ
What is wigolo?+
Wigolo is a local-first MCP server that provides AI agents with web search, fetch, crawl, extract, cache, and research capabilities. It runs on your machine with on-device models, requiring no API keys for core features and costing $0 per query.
How do I install and connect wigolo to my AI agent?+
Run 'npx wigolo init' to set up the local engine, or 'npx wigolo init --agents=claude-code,cursor' to automatically configure popular agents in one step. For other MCP clients, add 'npx -y wigolo' to your MCP configuration with the appropriate stdio transport settings.
Which AI clients and frameworks work with wigolo?+
Wigolo supports Claude Code, Cursor, Codex, Gemini CLI, OpenCode, VS Code, Windsurf, Zed, and Antigravity as MCP clients. It also integrates with LangChain, CrewAI, LlamaIndex, Vercel AI SDK, n8n, and any MCP-compatible client or self-hosted agent via REST API.
Do I need API keys to use wigolo?+
Core tools (search, fetch, crawl, extract, cache, find_similar) work with zero API keys. The research and agent tools optionally use an LLM for synthesis; you can provide a free Gemini key or run fully local with Ollama.
Is wigolo free to use?+
Yes, wigolo is free and open-source under AGPL-3.0. Core features cost $0 per query because they run locally. You can use it freely at work; the license only requires publishing modifications if you run it as a modified network service.
What are the system requirements?+
Wigolo requires Node.js version 20 or higher and approximately 1.5 GB of free disk space for the browser engine and on-device models. It runs on macOS, Linux, and Windows.
How do I install wigolo?+
Open the source repository on GitHub and follow its README. wigolo is a mcp server — MCP Agents Market links you directly to the official repo.
Is wigolo free?+
wigolo is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.