Best Drift AI Skills & MCP Servers

Pre-execution governance for AI agents. Intercepts MCP tool calls before execution with deterministic blocking, human-in-the-loop holds, and behavioral drift detection.

MCP server that gives AI agents (Claude, Cursor, Copilot) deep understanding of your codebase patterns, conventions, and architecture. Query patterns, security boundaries, call graphs in real-time.

dwic — the design auditor for Claude Code. MCP server that audits your design tokens + markup for WCAG contrast failures, mandated-accent drift, and structural gaps, then remembers findings across sessions.

MCP server that enforces multi-agent scope boundaries — prevents scope drift, work duplication, and infinite delegation loops in agentic systems

Pre-execution governance for AI agents. Intercepts MCP tool calls before execution with deterministic blocking, human-in-the-loop holds, and behavioral drift detection.

Behavioral governance layer for LLMs - monitors for hallucination, inconsistency, tone drift, and unsafe reasoning while managing stateful AI sessions

Vendor-neutral evidence review for AI-agent software work.

Local Markdown documentation hub with a built-in MCP server — coding agents create ADRs, draw diagrams and detect drift while you code.

Test your MCP servers for breaking changes. Checks capabilities, invokes tools, detects schema drift between versions.

Context synchronization layer for AI coding agents — ensure project continuity and eliminate memory drift automatically.

A deterministic compiler and linter for system architecture. Validate your architecture before you write code. OSS: structural validation + basic architecture lint (rule-based); FastAPI/Express export; OpenAPI document-shape; golden Docker/Makefile — no L

Non-custodial execution primitives for Solana. Best-execution routing across Jupiter Perps, Pacifica, Drift, and Flash Trade. 1 bps to open. Everything else is free. Your agent decides. Toreva executes. Every action receipted. Execution only — not financial advice.