pulse-fetch — Claude Code MCP server: setup
This MCP server fetches web pages, extracts useful content, and can work around anti-bot checks. It suits agents that lack built-in web fetching.
claude mcp add --env FIRECRAWL_API_KEY=<FIRECRAWL_API_KEY> --env BRIGHTDATA_API_KEY=<BRIGHTDATA_API_KEY> --env STRATEGY_CONFIG_PATH=<STRATEGY_CONFIG_PATH> --env OPTIMIZE_FOR=<OPTIMIZE_FOR> --env MCP_RESOURCE_STORAGE=<MCP_RESOURCE_STORAGE> --transport stdio pulse-fetch -- npx -y @pulsemcp/pulse-fetchWhat pulse-fetch does
pulse-fetch exposes a scrape tool for retrieving one web page at a time. It removes page noise and can return Markdown, HTML, screenshots, or structured data. A natural-language extraction request can target specific facts when an LLM is configured.
The server can return content directly or save it as an MCP Resource. Repeated requests use cached results, while forceRescrape: true asks for a new fetch. Firecrawl and BrightData provide the anti-bot path; the Claude Code setup requires FIRECRAWL_API_KEY, BRIGHTDATA_API_KEY, and LLM_API_KEY, so those keys are needed for the related workflows.
What it helps with
- extract the main text from a web article
- turn product pages into structured data
- retrieve content from an anti-bot protected page
- save fetched content as an MCP Resource
- request a fresh page version instead of cached content
Example prompts for the agent
- Extract the main content from
https://example.com/article. - Get structured product details from
https://shop.example.com/product/123. - Fetch
https://example.com/articleagain and bypass the cache.
How to install pulse-fetch
Platform CLI
claude mcp add --env FIRECRAWL_API_KEY=<FIRECRAWL_API_KEY> --env BRIGHTDATA_API_KEY=<BRIGHTDATA_API_KEY> --env STRATEGY_CONFIG_PATH=<STRATEGY_CONFIG_PATH> --env OPTIMIZE_FOR=<OPTIMIZE_FOR> --env MCP_RESOURCE_STORAGE=<MCP_RESOURCE_STORAGE> --transport stdio pulse-fetch -- npx -y @pulsemcp/pulse-fetchReplace <…> with your own values. 6 more environment variables are in the server README
Platform CLI
codex mcp add pulse-fetch --env FIRECRAWL_API_KEY=<FIRECRAWL_API_KEY> --env BRIGHTDATA_API_KEY=<BRIGHTDATA_API_KEY> --env STRATEGY_CONFIG_PATH=<STRATEGY_CONFIG_PATH> --env OPTIMIZE_FOR=<OPTIMIZE_FOR> --env MCP_RESOURCE_STORAGE=<MCP_RESOURCE_STORAGE> -- npx -y @pulsemcp/pulse-fetchReplace <…> with your own values. 6 more environment variables are in the server README
Config file
{
"mcpServers": {
"pulse-fetch": {
"command": "npx",
"args": [
"-y",
"@pulsemcp/pulse-fetch"
],
"env": {
"FIRECRAWL_API_KEY": "<FIRECRAWL_API_KEY>",
"BRIGHTDATA_API_KEY": "<BRIGHTDATA_API_KEY>",
"STRATEGY_CONFIG_PATH": "<STRATEGY_CONFIG_PATH>",
"OPTIMIZE_FOR": "<OPTIMIZE_FOR>",
"MCP_RESOURCE_STORAGE": "<MCP_RESOURCE_STORAGE>"
}
}
}
}Replace <…> with your own values. 6 more environment variables are in the server README
Config file
{
"servers": {
"pulse-fetch": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@pulsemcp/pulse-fetch"
],
"env": {
"FIRECRAWL_API_KEY": "<FIRECRAWL_API_KEY>",
"BRIGHTDATA_API_KEY": "<BRIGHTDATA_API_KEY>",
"STRATEGY_CONFIG_PATH": "<STRATEGY_CONFIG_PATH>",
"OPTIMIZE_FOR": "<OPTIMIZE_FOR>",
"MCP_RESOURCE_STORAGE": "<MCP_RESOURCE_STORAGE>"
}
}
}
}Replace <…> with your own values. 6 more environment variables are in the server README
Platform CLI
gemini mcp add -e FIRECRAWL_API_KEY=<FIRECRAWL_API_KEY> -e BRIGHTDATA_API_KEY=<BRIGHTDATA_API_KEY> -e STRATEGY_CONFIG_PATH=<STRATEGY_CONFIG_PATH> -e OPTIMIZE_FOR=<OPTIMIZE_FOR> -e MCP_RESOURCE_STORAGE=<MCP_RESOURCE_STORAGE> pulse-fetch npx -y @pulsemcp/pulse-fetchReplace <…> with your own values. 6 more environment variables are in the server README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about pulse-fetch
How do I install pulse-fetch in Claude Code?
Run `claude mcp add pulse-fetch -e FIRECRAWL_API_KEY=<FIRECRAWL_API_KEY> -e BRIGHTDATA_API_KEY=<BRIGHTDATA_API_KEY> -e LLM_API_KEY=<LLM_API_KEY> -- npx -y @pulsemcp/pulse-fetch`.
What does pulse-fetch do?
It gives the agent a scrape tool for fetching pages, cleaning their content, and returning it in several formats. It can cache results and extract selected facts from a page.
What credentials does pulse-fetch need?
The Claude Code setup uses FIRECRAWL_API_KEY, BRIGHTDATA_API_KEY, and LLM_API_KEY. The extract option also needs an LLM configuration.
