Parses codebases with AST to extract functions, classes, and files, enabling relationship-aware code review and impact analysis.
MIT
592,844 tools. Updated 2026-09-20 16:27
"Using LLM for Automated Code Review and Validation" matching MCP tools:
- Manage agent lifecycles, spawn specialized sub-agents, run automated code review and repair, orchestrate agent swarms, search persistent memory, and ingest tasks from external sources.MITDestructive
- Draft a reply to a Discord channel using your LLM, returning a suggested response for human review before sending. Use to prepare moderator replies or staff outreach.Apache 2.0
- Compares two versions of code to identify improvements, regressions, and neutral changes. Returns a merge recommendation for code review and refactoring validation.MIT
- Review code for correctness bugs, security issues, and simplification opportunities. Optionally narrow review to specific areas like concurrency or input validation.MIT
- Automatically review code changes with AI analysis and commit them if they pass security and quality checks.Apache 2.0
Matching MCP Servers
- AlicenseAqualityAmaintenanceMCP server that guides LLM security reviews step-by-step, tracking progress and ensuring all assigned source code is read before completing each plan step.4Apache 2.0
- AlicenseAqualityDmaintenanceAn MCP server that provides local code quality analysis for AI coding assistants, supporting file analysis, git diff review, and full project scanning with quality scoring.43MIT
Matching MCP Connectors
EU compliance checks for AI agents: sanctions, company, VAT ID, IBAN, email. Pay per call.
Multi-model code review: a panel of models + detectors return a pass/fail verdict. Paid via x402.
- Execute token migration with automated reference updates, validation, and rollback. Defaults to dry-run for safe preview before applying changes.MIT
- Submit chatbot validation results for contest documents, updating the Contests collection for Stage 2 validation before LLM normalization.MIT
- Retrieve formatted pull request details and review instructions to generate a comprehensive AI code review.MIT
- Submit a new term describing an AI phenomenology experience for the dictionary. Proposals undergo automated review including structural validation, deduplication, and quality scoring.MIT
- Review system design proposals and constraints with parallel LLM reviewers. Provide proposal text or file paths for context, plus explicit constraints and background.MIT
- Read source code files from a repository for code review, debugging, and understanding implementation details.MIT
- Submit a code snippet and specify its programming language to receive an automated code review.MIT
- Diagnose code for LLM inference issues. Receive a detailed report on latency, cost, throughput, and reliability with actionable fixes.Apache 2.0
- Get repository-specific code review guidelines to standardize pull request reviews in Bitbucket.MIT
- Get a comprehensive code evaluation across 45 judges using automated pattern detection and deep contextual analysis, delivering a combined verdict with scores, findings, and guidance to improve code quality.MIT
- Retrieves current uncommitted changes from a specified repository using git diff, enabling validation of work-in-progress code for ABAC review.MIT
- Analyze code or diffs using two parallel LLM reviewers to identify context-blind errors and improve code quality.MIT
- Challenge proposed code changes for scope creep, rewrites, contract assumptions, security implications, error handling, and missing validation using supplied evidence.MIT
- Check code for naming, comment coverage, long functions, duplicated blocks, and SEARCH/REPLACE diff issues using deterministic regex. Filters shallow problems before deep review.MIT
- Review git changes with an LLM to identify issues and improvements based on task context and project standards.MIT