"Xero" matching MCP servers:

A local code-intelligence engine for AI agents that indexes repositories into a PostgreSQL-backed code graph and serves structured, token-budgeted context over MCP and HTTP, enabling targeted queries on symbols, dependencies, contracts, and impact analysis.

locidx

Exposes compact-context MCP tools that outline large files, cap and summarize repo-wide searches, and run builds or tests while returning only grouped errors and key warnings. Guard hooks block whole-file reads, unbounded recursive greps, and raw build logs so coding sessions keep their context budget intact.

Enables MCP-compliant agents to audit source files for structural noise such as deep nesting, anonymous closures, raw conditionals, and duplicated literals, then apply behavior-preserving refactors like early returns, semantic predicates, and algebraic simplifications. Refactoring results are re-validated to confirm the noise score strictly decreases, with automatic rollback if the test suite fails.