Linkup
Wire live web search and sourced page fetches into your coding agent while you validate markets, check docs, or verify facts without leaving the IDE.
Overview
Linkup is an MCP server for the Idea phase that searches the web and fetches pages with sourced results for AI coding agents.
What is this MCP server?
- Web search and page fetch tuned for AI agents with attributable sources
- Stdio MCP transport via uvx (PyPI) or Docker OCI image
- Server version 1.0.2 from mcparmory registry on GitHub
- Fits Claude Code, Cursor, and other MCP-capable agents for in-session retrieval
- Reduces hallucinated citations by returning fetched content the model can quote
- Published server version 1.0.2
- 2 distribution packages: PyPI (uvx) and OCI Docker image
- Transport type: stdio
Community signal: 25 GitHub stars.
What problem does it solve?
Your agent cannot reliably answer “what does the docs say today?” or “who else ships this?” without live web access and traceable sources.
Who is it for?
Indie builders doing market, competitor, and API research inside Claude Code or Cursor who need citable web results on demand.
Skip if: Teams that need full browser automation, logins behind paywalls, or heavy scraping pipelines without an agent-first MCP setup.
What do I get? / Deliverables
After you register Linkup, your agent can run search-and-fetch tools in-session and ground answers in fetched pages you can verify.
- Registered stdio MCP server in your agent config
- In-session web search and page-fetch tools with sourced results
- Verifiable excerpts the agent can reference while coding
Recommended MCP Servers
Journey fit
Solo builders hit the Idea phase first when they need grounded, citable answers from the open web before committing to a product direction. Research is where agent-driven search with sources replaces manual tab-hopping for competitors, APIs, and trend checks.
How it compares
MCP retrieval server for search and fetch, not a journey-wide brainstorming or planning skill.
Common Questions / FAQ
Who is com.mcparmory/linkup for?
Solo builders and small teams using MCP-enabled coding agents who need grounded web search and page content during research and implementation.
When should I use com.mcparmory/linkup?
Use it whenever the agent must check current documentation, competitors, or factual claims on the public web with sources instead of memory alone.
How do I add com.mcparmory/linkup to my agent?
Add the stdio MCP server to your client config using the mcparmory-linkup PyPI package with uvx or the ghcr.io/mcparmory/linkup Docker image, then restart the agent.