cnighswonger/claude-code-cache-fixConnectors
Fixes prompt cache regression in Claude Code that causes up to 20x cost increase on resumed sessions
434
baryhuang/
mcp-hubspot
baryhuang/mcp-hubspotConnectors
A Model Context Protocol (MCP) server that enables AI assistants to interact with HubSpot CRM data, providing built-in vector storage and caching mechanisms help overcome HubSpot API limitations while improving response times.
128
firish/
webfetch
firish/webfetchConnectors
Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at 66% lower cost and up to 88% fewer tokens, plus a precision-tuned semantic caching with query-dependant TTL that no API offers.
55
moonlin1213/
cove-book-forge-mcp
moonlin1213/cove-book-forge-mcpConnectors
Turn PDF and EPUB books into cached AI analysis, Obsidian notes, and installable Codex/Claude Agent Skills through an open MCP server.
37
ooples/
token-optimizer-mcp
ooples/token-optimizer-mcpConnectors
Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.
516