$ loading_
Scan codebases for incompleteness and quantify LLM context drift risk.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "MCP Drift State Tracker" yet — see the docs or source repo.
Scan this multi-language codebase, identify stubs, missing imports, and structural incompleteness, and return an overall drift score.
A list of detected issues plus a score representing codebase context drift.
Inspect the current code state, detect placeholder implementations, missing references, or structural breaks, and quantify their impact on context integrity.
Detected integrity issues and a drift score that can be used to track degradation.
Scan this polyglot project and summarize incomplete implementations and dependency reference issues to judge whether the repository is drifting away from a maintainable state.
A maintenance-oriented findings summary with a quantified drift indicator.
Developers can use it after LLM-generated or LLM-edited changes to scan for stubs, missing imports, and structural gaps, helping determine whether context drift has become significant.
When a team maintains a repository with multiple languages, it can serve as a structural integrity checker to find incomplete states across the codebase and quantify risk.
Researchers or engineering teams can use the drift score to observe context erosion over time and support later remediation or governance work.
It is an MCP server that scans multi-language codebases for stubs, missing imports, and structural incompleteness, then quantifies LLM context erosion with a drift score.
The provided information explicitly mentions three issue types: stubs, missing imports, and structural incompleteness. For more detailed coverage, see the source repository.
The available material only states that it is an MCP server and does not provide installation steps, runtime requirements, or key details; see the source repository for specifics.
Understand codebases, detect conventions, and retain decisions across sessions.
Audit project portfolios against GitHub conversationally to detect drift and anomalies.
Scan codebases for LLM usage, AI frameworks, and exposed secrets.
Analyze code structure and Git history while drastically reducing AI token usage.
Use safe MCP tools for calculation, search, drift checks, eval comparison, and grading.
Run dev checks and get compact error summaries for faster debugging.