[](https://glama.ai/mcp/servers/natiixnt/redcon) - Deterministic repository context packing for AI coding agents: selects, compresses, caches, and budgets only the files a task needs. Measured 83% fewer…
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Not distributed through a package registry we index.
Attributed to the source that supplied each field. Treated as claims, not facts.
[](https://glama.ai/mcp/servers/natiixnt/redcon) - Deterministic repository context packing for AI coding agents: selects, compresses, caches, and budgets only the files a task needs. Measured 83% fewer input tokens at the same task coverage, no LLM in the loop. One MCP server for Claude Code, Cursor, Windsurf, Cline, and Zed. `pip install redcon`
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.
Search and read the public Applivery docs (MDM & app distribution). Read-only, no auth.