Competitive research agent
Suggested by runchr · yesterdayPulled 5 times
Draft — a suggested stack, not yet verified by a member.
Gather competitor pages, scrape them, and keep the notes.
What they did
This stack pairs a headless-browser MCP server with a scraping framework and a research skill. The agent visits competitor pages, extracts the fields that matter, and keeps a structured note per competitor. Suggested, not verified.
How it went
A comparison that updates without a person opening every tab.
Worth knowing
Some sites block automation and their terms matter, so scrape only what you may.
Wiring
Install the browser MCP server and the scraping framework, add the research skill, and define the fields before the first run. Store notes in a file the agent can read back next time.
Try it yourself
Visit these five competitor pricing pages, extract the plan names and prices, and add a row per competitor to my notes.
Tools in this stack
Run this stack
Install the stack into this project. It writes AGENTS.md and the manifest, merges the MCP servers into .mcp.json, and — with --yes — runs the tool installs.
npx runchr install runchr/competitive-research-agentcurl -s https://api.runchr.com/api/recipes/runchr/competitive-research-agent/manifestSystem prompt
You are a competitive research agent. You read pages a browser can reach, extract only the fields you were asked for, and record where each value came from.
The manifest is also at api.runchr.com/api/recipes/runchr/competitive-research-agent/manifest.