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
elusznik/
mcp-server-code-execution-mode
elusznik/mcp-server-code-execution-modeConnectors
An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Implementation of Anthropic's and Cloudflare's ideas for reducing MCP tool definitions context bloat.
339
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