"Using local LLMs for code writing, reviewing, and rule generation" matching MCP servers:

Safe local MCP server for Windows to list, read, search, patch, backup, and verify code files in allowed folders, with Git integration and dry-run diffs.

Profile-driven MCP server for safely inspecting and changing local Git repositories via a Streamable HTTP endpoint with deny-by-default security.

Enables LLM agents to manage projects, track issues, log work, and integrate with Git. Provides 23 MCP tools for full project management capabilities.

An MCP server that integrates AI assistants like Claude with GitLab's merge requests, allowing them to review code changes, add comments, and approve/unapprove merge requests directly through the GitLab API.

Enables Claude Code to record a verifiable history of code changes with before/after and rationale, and to propose changes that users can accept or discard, all reviewable on a local web timeline.

A security-first MCP server that enables clients to inspect and edit multiple local repositories via configured aliases, with read-only Git access and allowlisted test commands.

Odds are, most of what you want to build is already open source. Tell your AI agent what you're making, and it finds it: which repos to use as they are, which to adapt, and what's left for you to write. Every repo it names is real, licensed for your use or flagged, and checked live.

Analyzes codebases using Repomix and LLMs to provide structured code reviews with specific issues and recommendations, supporting multiple LLM providers including OpenAI, Anthropic, and Gemini.

Deterministic code review MCP server that provides tools for file selection, rule matching, comment positioning, and reflection, ensuring stable review quality without LLM calls.

Enables AI clients like ChatGPT or Codex to manage files and local Git repositories within an explicitly authorized workspace, with server-enforced path boundary checks and optional remote Git operations.

A local MCP server that connects Claude Desktop, Claude Code, and Claude Chat to your Azure DevOps organization, enabling querying work items, reviewing pull requests, triggering pipelines, searching code, managing test plans, and updating wikis using plain language.

A production-grade MCP server for the Code-Fundi API, enabling AI agents to map codebases, search semantically, and analyze blast radius. It provides tools for repository management, AI-powered research, and impact analysis before shipping changes.

For people who want their AI to run the build, read the error and check the dev server itself, instead of pasting output into chat. Works with Claude Desktop (one-click installer), Cursor, Claude Code and Cline. Runs locally over stdio or HTTP, no telemetry. A seatbelt for everyday mistakes, not a sandbox.

An experimental MCP server that enables AI assistants to interact with VS Code workspaces through file operations, code execution, and Git management. It also provides tools for Docker integration, project scaffolding, and secure command execution using project-specific configurations.

A comprehensive MCP server that provides AI assistants with tools for file system management, Git integration, and shell command execution. It features specialized code utilities for analysis, formatting, and linting to enhance development workflows within Claude Desktop.

Secure agent coding runtime for local Git repos with policy enforcement, RBAC, sessions, approval workflow, and sandboxed writes, optionally connectable to ChatGPT via Secure MCP Tunnel.

Enables comprehensive GitHub PR reviews through Cursor's AI by fetching PR diffs, running static analysis tools (ESLint, Prettier, TypeScript, Semgrep), executing tests, and generating detailed code review reports with inline comments.

A local, zero-dependency MCP server that cuts coding-agent round-trips by aggregating search, read, edit, exec, git, and savings tools into single, validated calls, with cost tracking and no data leaving the machine.

Enables Claude AI to run terminal commands, perform file operations, and manage git in a project directory via the Model Context Protocol.

Enables a remote Hermes agent to inspect allowed files and propose patch/check requests on a local Git workspace, while the local operator retains approval and applies changes from isolated snapshots.