token-optimization MCP servers & tools

Local proxy that collapses N downstream MCP servers into 4 meta-tools with progressive tool discovery (measured: 122 tools → 4, 28.6K tokens of definitions saved), compresses large tool outputs (HTML→Markdown, JSON structure summarization, base64 stripping — 60–95% measured on real pages/APIs) with full-output retrieval via readmore, and prints a per-session token-savings report. Security-relevant outputs are never silently compressed. Install: npx -y context-firewall --config config.json

Reduces MCP tool description token costs by 40-70% through pure text schema distillation.

Token-efficient C#, Razor, and .NET file views for AI assistants. 50-95% token reduction via Roslyn.

Index your codebase. AI searches instead of re-reading files. 94% token savings.

Save up to 80% tokens when AI reads code via AST-aware structural reading

Lossless context compression: 2-8x fewer tokens, byte-exact recovery, search inside payloads

Deterministic context packing for AI coding agents; measured 83% fewer input tokens, local.

Intelligent MCP proxy that reduces token usage by exposing only mcp_search and mcp_call.

Read large logs, JSON and docs in a fraction of the tokens. Offline, fact-preserving optimizer.

Profile LLM context: token breakdown, wasted-context findings and fixes for chats and agents.