pulse-fetch

MCP server that extracts clean, structured content from web pages with anti-bot bypass capabilities.

stdio v0.2.14

Connection Configuration

Add this to your AI agent's MCP config file to connect.

Run in your terminal:

claude mcp add com.pulsemcp.servers--pulse-fetch -- npx

Transport

stdio

Authentication

None

Version

v0.2.14

Server Name

com.pulsemcp.servers/pulse-fetch

Last Updated

Sep 9, 2025

How to install and connect this MCP server.

Environment variables you must provide when running this server.

Variable	Description	Required
`FIRECRAWL_API_KEY` secret	API key for Firecrawl service to bypass anti-bot measures	Optional
`BRIGHTDATA_API_KEY` secret	Bearer token for BrightData Web Unlocker service	Optional
`STRATEGY_CONFIG_PATH`	Path to markdown file containing scraping strategy configuration	Optional
`OPTIMIZE_FOR`	Optimization strategy for scraping: cost or speed	Optional
`MCP_RESOURCE_STORAGE`	Storage backend for saved resources: memory or filesystem	Optional
`MCP_RESOURCE_FILESYSTEM_ROOT`	Directory for filesystem storage (only used with filesystem type)	Optional
`SKIP_HEALTH_CHECKS`	Skip API authentication health checks at startup	Optional
`LLM_PROVIDER`	LLM provider for extract feature: anthropic, openai, openai-compatible	Optional
`LLM_API_KEY` secret	API key for the chosen LLM provider	Optional
`LLM_API_BASE_URL`	Base URL for OpenAI-compatible providers	Optional
`LLM_MODEL`	Specific model to use for extraction	Optional