About
wigolo is an MCP server for web research workflows. The official source for this listing is the public GitHub repository at https://github.com/KnockOutEZ/wigolo. The upstream description says: 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. GitHub metadata reviewed during this run showed 1,314 stars and a latest public push dated 2026-07-18. Builders should evaluate wigolo as a local MCP component, not as a generic SaaS listing. Add it to a disposable MCP client first, confirm the commands it exposes, and verify which network calls, local files, caches, or crawling behavior it uses. Web research tools can collect a lot of context quickly, so teams should define clear boundaries before connecting them to private repositories or internal planning documents. The main fit is AI coding agents that need search, fetch, crawl, or research operations while staying close to the developer machine. If the repository setup matches your client, wigolo can reduce the need for separate hosted search APIs during coding sessions. If a team needs managed compliance, central billing, or audited web access, it should compare this local-first path with a hosted research provider. Pricing is listed as open-source repository access because the selected source is public GitHub. The source signal states no API keys, no cloud, and zero dollars per query, but operating cost can still include local compute, network usage, and any model API calls made by the surrounding agent. Verification note: OpenTools used the repository URL, GitHub API metadata, README text, and the triage source signal. It does not invent undocumented MCP tools or private roadmap claims. README excerpt reviewed from source: Local first web intelligence for AI agents — no keys, no cloud, no metered bill. works with Claude Code · Cursor · Codex · Gemini CLI · VS Code · Windsurf · Zed · Antigravity and beyond LangChain · CrewAI · LlamaIndex · Vercel AI SDK · n8n & self hosted agents · any MCP client · plain REST [](https://www.npmjs.com/package/wigolo) [](https://github.com/KnockOutEZ/wigolo/stargazers) [](https://nodejs.org) [](https://modelcontextprotocol.io) []( license) []( beta feedback) Quickstart · Tools · Why wigolo · Benchmark · Docs · Examples · Feedback · FAQ wigolo gives an AI agent one durable surface for everything web related — search, fetch, crawl, extract, cache, find simil
Features
- Provides local-first search, fetch, crawl, and research capabilities over MCP
- Built for AI coding agents that need web context without a separate cloud API key
- Public beta source repository that builders can inspect before adding to an MCP client
- Useful when coding agents need source material from the web during implementation or review
Use Cases
AI coding agent users
Give an MCP-compatible coding agent local web search, fetch, crawl, and research operations.
Developer tooling teams
Test a no-cloud research server before deciding whether to standardize a hosted web research API.
What This Server Can Do
MCP servers expose three types of capabilities to AI clients. Here's what wigolo supports.
Tools
Supported4 toolsFunctions your AI client can call to perform actions — like querying a database, creating a file, or calling an API.
How to use: Tools run automatically when your AI client decides they're needed. Ask your AI assistant to perform a task, and it will invoke the right tool.
Resources
Not availableThis server does not expose read-only data resources.
Prompts
Not availableThis server does not provide pre-built prompt templates.
For the full list of available tools, resources, and prompts, check the README on GitHub.
Available Tools (4)
searchSearch web operation exposed for MCP-compatible AI coding agents. Verify exact arguments against the upstream README before production use.
fetchFetch web operation exposed for MCP-compatible AI coding agents. Verify exact arguments against the upstream README before production use.
crawlCrawl web operation exposed for MCP-compatible AI coding agents. Verify exact arguments against the upstream README before production use.
researchResearch web operation exposed for MCP-compatible AI coding agents. Verify exact arguments against the upstream README before production use.