Pulse Fetch MCP Server

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

claude mcp add pulse-fetch -- npx -y @pulsemcp/pulse-fetch

{
  "mcpServers": {
    "pulse-fetch": {
      "args": [
        "-y",
        "@pulsemcp/pulse-fetch"
      ],
      "command": "npx"
    }
  }
}

[mcp_servers.pulse-fetch]
command = "npx"
args = ["-y", "@pulsemcp/pulse-fetch"]

{
  "mcpServers": {
    "pulse-fetch": {
      "args": [
        "-y",
        "@pulsemcp/pulse-fetch"
      ],
      "command": "npx"
    }
  }
}

{
  "mcpServers": {
    "pulse-fetch": {
      "args": [
        "-y",
        "@pulsemcp/pulse-fetch"
      ],
      "command": "npx"
    }
  }
}

This one needs environment variables set before it will start: FIRECRAWL_API_KEY (API key for Firecrawl service to bypass anti-bot measures.), BRIGHTDATA_API_KEY (Bearer token for BrightData Web Unlocker service.), STRATEGY_CONFIG_PATH (Path to markdown file containing scraping strategy configuration.), OPTIMIZE_FOR (Optimization strategy for scraping: cost or speed.), MCP_RESOURCE_STORAGE (Storage backend for saved resources: memory or filesystem.), MCP_RESOURCE_FILESYSTEM_ROOT (Directory for filesystem storage of resources.), SKIP_HEALTH_CHECKS (Skip API authentication health checks at startup.), LLM_PROVIDER (LLM provider for extraction: anthropic, openai, or openai-compatible.), LLM_API_KEY (API key for the chosen LLM provider.), LLM_API_BASE_URL (Base URL for OpenAI-compatible LLM providers.), LLM_MODEL (Specific LLM model to use for extraction.). The author declared them in the registry entry; get the values from the project itself.