MCP Tools DirectoryAbout this integration
Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching
- Transport
- stdio
- Authentication
- none
- Initial setup
- none
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.1.3
- Package
- webfetch-llm
- Last compatibility test
- Not independently tested
Connect your agent
webfetch-llmPublisher README and executable manifest reviewed from pinned captures; package and integration endpoint were not executed or independently security-audited.
Capabilities: Search the web, Fetch and extract pages, Cache and rank results
Connected profiles
Additional details
Registry identifier
io.github.firish/webfetch
Source ↗ · Checked 2026-09-17Published version
0.1.3
Source ↗ · Checked 2026-09-17Metadata license
CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17Package ecosystem
pypi
Source ↗ · Checked 2026-09-17Source artifact
webfetch-llm
Source ↗ · Checked 2026-09-19Source manifest version
0.1.3
Source ↗ · Checked 2026-09-19Unattended configuration
Publisher documents registering and launching the webfetch-mcp console server.
Source ↗ · Checked 2026-09-19Authentication and prerequisites
DuckDuckGo works without a key; optional provider keys add search engines.
Source ↗ · Checked 2026-09-19Connection configuration
MCP clients launch webfetch-mcp directly or through uvx.
Source ↗ · Checked 2026-09-19Review scope
Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19