Knowledge Base Context Router MCP

Cut LLM Token Costs by Routing Code Context

A standardized interface for AI assistants to navigate, understand, and interact with your repository's engineering context.

Launching Soon...

The Cost of Codebase Blindness:
The Token Tax

AI coding agents are incredibly powerful, but they operate blind. When asked a simple question like "what functions call ProcessPayment?", agents typically traverse your repository file-by-file.

They grep across files, read entire modules, and follow imports sequentially. This raw document exploration can easily burn 40,000+ tokens on a single simple query. Over a development session, this "token tax" leads to runaway API costs, slow response times, and frequent context limit exhaustion.

A Structural Map for
AI Coding Agents

The Context Router MCP solves token bloat by mapping your repository's skeletal structure, classes, functions, imports, exports, and relationships. It exposes this schema directly to your AI agent, allowing it to navigate code boundaries instantly.

Structural Navigation

Instead of guessing filenames or reading entire directories, the agent queries codebase skeletons to trace definitions, imports, and cross-references.

Context Compression

The agent retrieves only the relevant code signatures and boundaries, stripping out unnecessary implementation details to keep payloads compact and fast.

Benchmarks: Graph vs. File-by-File Search

Transitioning from blind file crawling to structural context routing reduces token usage by 99.2% on average.

Query Type Penqwin Context Router File-by-File Search Savings
Find function by pattern ~200 tokens ~45,000 tokens 225x savings
Trace call chain (depth 3) ~800 tokens ~120,000 tokens 150x savings
Dead code detection ~500 tokens ~85,000 tokens 170x savings
List all HTTP routes ~400 tokens ~62,000 tokens 155x savings
Architecture overview ~1,500 tokens ~100,000 tokens 67x savings
Total Session Average ~3,400 tokens ~412,000 tokens 120x reduction

Designed for
Engineering Teams

The Context Router MCP is engineered for speed and footprint efficiency, easily scaling to compile and route structural blueprints for enterprise-grade repositories.

Sub-Second Re-Indexing: Average-sized repositories are parsed and indexed in milliseconds, updating your agent’s memory instantly as you type.
Instant Team-Wide Sync: The structural mapping is kept continuously in sync with your GitHub main branch, making codebase blueprints immediately available to the entire team without individual re-indexing.