Pulse Fetch MCP Server
This is an MCP (Model Context Protocol) Server that pulls specific resources from the open internet into context, designed for agent-building frameworks and MCP clients that lack built-in fetch capabilities.
People who work with Firecrawl and Brightdata and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.
One of 28 MCP servers published from pulsemcp/mcp-servers. Stars and repository activity are shared across all of them. See all 28 →
VERIFIED ACTIVE
LAST COMMIT 2026-08-30 · VERIFIED 2026-09-30
MIT · TypeScript servers · how we verify → /methodology
01 · Install Pulse Fetch
before you install - you'll need
Set FIRECRAWL_API_KEY, BRIGHTDATA_API_KEY, STRATEGY_CONFIG_PATH, MCP_RESOURCE_STORAGE, MCP_RESOURCE_FILESYSTEM_ROOT before connecting. OPTIMIZE_FOR is optional or environment-specific per the README.
Claude Code
claude mcp add pulsemcp-mcp-servers-productionized-puls -- npx -y @pulsemcp/pulse-fetch Claude Desktop / Cursor / VS Code - add to config
{
"mcpServers": {
"pulsemcp-mcp-servers-productionized-puls": {
"command": "npx",
"args": [
"-y",
"@pulsemcp/pulse-fetch"
]
}
}
} Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.
Using another client? Same JSON, different key
Claude Desktop · mcpServers
Cursor · mcpServers
VS Code · servers
Windsurf · mcpServers
Zed · context_servers
Cline · mcpServers
Roo Code · mcpServers
Continue · mcpServers
LibreChat · mcpServers
Gemini CLI · mcpServers
Codex CLI · mcp_servers
Full setup guides: every client.
02 · Evidence
Security posture
What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.
runs as local process (stdio) - runs on your machine with your user's permissions
license MIT - declared in the repository
npm package @pulsemcp/pulse-fetch - published under the repo owner's npm scope (@pulsemcp)
registry vendor namespace com.pulsemcp - domain-verified with the official MCP registry
03 · What Pulse Fetch can do
Prose above is summarized from the project's README and registry record - no invented capabilities.
Latest releases
[email protected] · 2026-07-10
Fixed · Gmail deep-links emitted by list_email_conversations, search_email_conversations, get_email_conversation, and send_email now use the form instead of Two independent defects made the old links fail to open the…
[email protected] · 2026-07-09
Added · create_oauth_client tool (keys group, write): mints a non-interactive Tailscale OAuth client (client_id + client_secret) with configurable scopes and ACL tags. Unlike create_auth_key - which only enrolls…
[email protected] · 2026-07-06
Added · set_account_balance_history (manage group): edit a manual account's recorded daily balance snapshots. Previously the server could read balance history (get_account_balance_history) but had no write counterpart…
04 · Who maintains Pulse Fetch
pulse-fetch is maintained by pulsemcp. We track 29 MCP servers from pulsemcp - 28 actively maintained, 80 combined GitHub stars, oldest repo from May 2025. Full record: all servers from pulsemcp.
- slack MCP server for Slack - read/write messages, manage threads, and react to messages. ★ 80
- playwright-stealth Browser automation using Playwright with optional stealth mode to bypass anti-bot protection. ★ 80
- onepassword MCP server for interacting with 1Password via the CLI to read and manage credentials. ★ 80
- gmail MCP server for Gmail with OAuth2 (personal) and service account (Workspace) support. ★ 80
- google-flights MCP server for searching Google Flights - flight search, date grid pricing, and airport lookup. ★ 80
- appsignal MCP server for AppSignal - get alert details, search logs, and retrieve logs within time ranges. ★ 80
05 · Facts
- repository
- github.com/pulsemcp/mcp-servers
- category
- web scraping - actively maintained as of 2026-09-30.
- registry
- com.pulsemcp/pulse-fetch (active, first published 2026-05-18 · 2 versions)
- packages
- npm:@pulsemcp/pulse-fetch
06 · Pulse Fetch FAQ
What is Pulse Fetch?
This is an MCP (Model Context Protocol) Server that pulls specific resources from the open internet into context, designed for agent-building frameworks and MCP clients that lack built-in fetch capabilities.
Is Pulse Fetch still maintained?
Yes - as of 2026-09-30, its last commit was 2026-08-30. We re-verify nightly.
How do I install Pulse Fetch?
Run `npx -y @pulsemcp/pulse-fetch`. The README documents 6 environment variables (FIRECRAWL_API_KEY, BRIGHTDATA_API_KEY, STRATEGY_CONFIG_PATH…) to set first. Set FIRECRAWL_API_KEY, BRIGHTDATA_API_KEY, STRATEGY_CONFIG_PATH, MCP_RESOURCE_STORAGE, MCP_RESOURCE_FILESYSTEM_ROOT before connecting. OPTIMIZE_FOR is optional or environment-specific per the README. You can also paste the ready-made client config above.
Does Pulse Fetch run locally?
Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.
07 · Alternatives to Pulse Fetch
Alternatives to Pulse Fetch
Maintained web scraping servers if Pulse Fetch isn't the fit.
- Apify MCP Server Extract data from any website with thousands of scrapers, crawlers, and automations on Apify Store ⚡ ★ 8,922 · 2026-09-29
- Firecrawl MCP Server MCP server for Firecrawl - web search, scraping, and biomedical/arXiv paper search. ★ 7,536 · 2026-09-30
- Exa Connect AI agents to Exa for web search, content fetching, and multi-step research. ★ 5,058 · 2026-09-23
- Tavily MCP MCP server for advanced web search using Tavily ★ 2,416 · 2026-09-29
- CRW Web Scraper Open-source web scraper for AI agents with scrape, crawl, and map tools ★ 1,088 · 2026-09-30
- Open Brand Extract brand assets (logos, colors, backdrop images, brand name) from any website URL ★ 799 · 2026-05-12
Pairs well with
Servers that cover what Pulse Fetch doesn't - only shown when the pairing reason fits the companion.
- SearXNG Search → search companion search · ★ 1,268
- Server Search → search companion search · ★ 39,168
- Supabase → database companion database · ★ 2,926
- MongoDB MCP Server → database companion database · ★ 1,137
- Codebase Memory → memory companion memory · ★ 45,519
- Memorix → memory companion memory · ★ 819
More web scraping MCP servers · Fitter · Doc Pull · Rampify · Pyre Crawl · Scrape Badger
More TypeScript MCP servers · Pulse Subregistry · SVG Tracer · Google Trends MCP · Purmemo · CLI (pushtodisplay) · see all