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
capitalparser/
notebooklm-wiki-pipeline
capitalparser/notebooklm-wiki-pipelineConnectors
Turn Google Drive PDFs into Obsidian wiki notes via NotebookLM MCP without loading full PDFs into Claude context
94
yvgude/
lean-ctx
yvgude/lean-ctxConnectors
LeanCTX — Context Intelligence for AI systems.
3.8k
jgravelle/
jdocmunch-mcp
jgravelle/jdocmunch-mcpConnectors
The leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing
203
hunhee98/
pluck
hunhee98/pluckConnectors
MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup
42
jgravelle/
jdatamunch-mcp
jgravelle/jdatamunch-mcpConnectors
Token-efficient MCP server for tabular data retrieval. Index CSV/Excel files, query rows, aggregate — 99%+ token savings vs raw file reads.
81
juyterman1000/
entroly
juyterman1000/entrolyConnectors
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.
443
jgravelle/jcodemunch-mcpConnectors
Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
2.7k