Pulse Fetch
This MCP server provides intelligent web scraping capabilities with automatic strategy selection and anti-bot bypass integration, built by PulseMCP using TypeScript and the Model Context Protocol SDK. It implements a three-tier fallback system that automatically chooses between native fetch, Firecrawl API for enhanced content extraction, and BrightData Web Unlocker for protected sites, while learning and saving successful strategies for future requests to optimize performance over time. The implementation features configurable optimization modes (cost vs speed), resource caching with both memory and filesystem storage backends, content processing with truncation and pagination support, and automatic URL pattern learning that builds a markdown-based configuration file to remember which scraping methods work best for specific domains and URL patterns.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- browser-automation
- Source
- PulseMCP
- Author type
- human
- Updated
- 2026-04-29
Use via MCP
Resolve Pulse Fetch from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.