"Loop" matching MCP servers:

An AI debugging agent MCP server that enables autonomous plan-act-observe debugging workflows, allowing repository exploration, code inspection, human-approved edits, and test execution through structured MCP tools.

MCP server that makes AI agents get SAP CAP/CDS right by providing curated knowledge and a feedback loop with real validation against cds compile.

A model-free MCP server that enforces an adversarial, Karl Popper-style review loop for Claude Code, catching emergent interaction bugs before implementation.

Wraps the cellc CellScript compiler so that an AI can write, check, explain, and inspect CKB Cell contracts in a local agentic loop.

Agent-first programming language: agents produce JSON AST, the compiler validates, type-checks, effect-checks, verifies contracts via Z3/SMT, and compiles to WASM. 19 MCP tools for the full compile-and-execute loop.

An MCP bridge that enables Claude Code to consult the Kimi AI model in a structured challenge-loop for code review, debugging, and architecture evaluation.

Compiler-in-the-loop steering for coding agents - Cursor and Claude Code. It runs your workspace's real language server on each edit, extracts diagnostics scoped to the changed lines and type signatures, and feeds that back to the coding agent.

Enables AI-powered code review and improvement, including analysis, refactoring suggestions, and automatic test generation, with an optional agentic loop for iterative refinement.

Verify-and-repair secure-coding harness that generates, hardens, audits, and scores Go code with a build and security scan feedback loop, and includes a transparent proxy to harden any client automatically.

An AI-powered server for code analysis, requirements validation, and automated fix proposals with human-in-the-loop confirmation. It supports multiple LLM providers and ensures safe file modifications through automatic backups and path validation.

An autonomous code-reasoning agent that parses repositories using tree-sitter, indexes symbols into SQLite, and answers questions about the codebase through an agentic loop powered by Claude via OpenRouter.

Architectural sensor for Python codebases. Scores structural health (modularity, acyclicity, depth, equality), detects import cycles, enforces YAML layer rules, and runs a snapshot/diff loop so AI-assisted edits do not silently regress structure.

Deterministic repository context packing for AI coding agents: selects, compresses, and budgets only the files a task needs. Measured 83% fewer input tokens at the same task coverage, fully local, no LLM in the loop.

Enables coding agents to capture and inspect running projects, resolve real assets from free sources, and check source for design tells, providing an evidence loop for improving websites, games, and motion.

An adversarial code verification system that uses a Verifier-Critic debate loop to systematically uncover security, correctness, and performance issues. It implements the Socratic method to provide deep semantic analysis and dialectical reasoning beyond traditional static linting.

Enables coding agents to navigate large codebases through a tree-sitter symbol graph, retrieve compact path:line-annotated context, and run a SNIPE fix loop with live dashboard updates on every save.

Provides a set of MCP tools to clone and analyze arbitrary MCP server repositories, run static and dynamic security probes in isolated Docker containers, and produce vulnerability verdicts with a human-in-the-loop approval step before filing public reports.

Headless reverse engineering MCP server integrating IDA Pro for static analysis and x64dbg for dynamic debugging via controlled MCP tools.

Enables analyzing and optimizing context window token usage by measuring, compressing, and eliminating waste from MCP tool definitions.

A navigable symbol map of your codebase for coding agents, enabling efficient code navigation and reading only relevant symbols instead of entire files.