Local Web Search
This MCP server implementation provides a local web search capability, integrating with a headless browser to perform Google searches and extract content from web pages. Developed by Frad Lee, it offers features such as customizable search queries, result limiting, domain exclusion, and content truncation. The server uses the Readability library to clean and parse web content, converting it to markdown format. It's designed for AI assistants and other MCP-compatible clients that require up-to-date web information without direct internet access. The implementation is particularly useful for tasks like research, content aggregation, and information retrieval across various domains.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
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
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Local Web Search 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.