Pulse Fetch MCP server
{
"mcpServers": {
"com-pulsemcp-pulse-fetch": {
"command": "npx",
"args": [
"-y",
"@pulsemcp/pulse-fetch@latest"
],
"env": {
"AGENT_ORCHESTRATOR_BASE_URL": "https://...",
"FLY_IO_API_TOKEN": "<fly_io_api_token>"
}
}
}
}{
"mcpServers": {
"com-pulsemcp-pulse-fetch": {
"command": "npx",
"args": [
"-y",
"@pulsemcp/pulse-fetch@latest"
],
"env": {
"AGENT_ORCHESTRATOR_BASE_URL": "https://...",
"FLY_IO_API_TOKEN": "<fly_io_api_token>"
}
}
}
}{
"mcpServers": {
"com-pulsemcp-pulse-fetch": {
"command": "npx",
"args": [
"-y",
"@pulsemcp/pulse-fetch@latest"
],
"env": {
"AGENT_ORCHESTRATOR_BASE_URL": "https://...",
"FLY_IO_API_TOKEN": "<fly_io_api_token>"
}
}
}
}{
"servers": {
"com-pulsemcp-pulse-fetch": {
"command": "npx",
"args": [
"-y",
"@pulsemcp/pulse-fetch@latest"
],
"env": {
"AGENT_ORCHESTRATOR_BASE_URL": "${input:agent_orchestrator_base_url}",
"FLY_IO_API_TOKEN": "${input:fly_io_api_token}"
}
}
},
"inputs": [
{
"id": "agent_orchestrator_base_url",
"type": "promptString",
"description": "Agent orchestrator base url",
"password": true
},
{
"id": "fly_io_api_token",
"type": "promptString",
"description": "Fly io api token",
"password": true
}
]
}{
"mcpServers": {
"com-pulsemcp-pulse-fetch": {
"command": "npx",
"args": [
"-y",
"@pulsemcp/pulse-fetch@latest"
],
"env": {
"AGENT_ORCHESTRATOR_BASE_URL": "https://...",
"FLY_IO_API_TOKEN": "<fly_io_api_token>"
}
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsoninstall npx -y @pulsemcp/pulse-fetchversion 0.3.3
What it does
Pulse Fetch is an MCP server for retrieving and extracting content from web resources. It handles anti-bot mechanisms and content extraction, designed for agent frameworks and MCP clients that need to fetch web data into context.
- Retrieve and extract text content from web pages to provide current information to LLM agents.
- Bypass common anti-bot protections when fetching web resources for analysis.
- Cache fetched resources to reduce repeated network requests and extraction overhead.
Tools this server exposes
| Tool | Does |
|---|---|
| fetch | Fetch a web resource and extract its content, with support for anti-bot bypass and HTML noise removal. |
This entry comes from the registry but points to no public repository, so there is nothing to check: no commit history, no source, no tool list. It is listed for completeness and left out of search engines.
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.