"Integrating Claude Desktop with a Local LLM using the LMStudio API" matching MCP servers:

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.

Provides a read-only MCP bridge that lets Claude Web inspect workspace files, git state, and recorded test results while Codex remains the sole executor of changes.

MCP server for reviewing code changes using LLMs, supporting Copilot, Ollama, and OpenAI-compatible endpoints.

MCP server for managing a project backlog as Markdown files in Git, enabling AI agents to read, create, and update tasks programmatically.

A read-only MCP connector that lets ChatGPT on the web plan tasks and independently review real Git diffs for local coding agents across many registered projects through one shared OAuth-protected hub connection, with no API key required. It exposes only file reads — never edits or shell tools — so the coding agent keeps full ownership of execution while the web subscription handles the reasoning and review.

A stdio MCP server that lets Codex Desktop/CLI delegate implementation tasks to Claude Code CLI with workspace validation, Git status checks, and session resume capabilities.

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.

Adds a live git branch status bar to the Claude interface for monitoring multiple repositories simultaneously. It provides tools for managing repository tracking and visibility through natural language commands.

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.

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.

MCP server for interacting with GitLab API, supporting dynamic tool selection and enterprise-grade security.

Provides bounded, read-oriented access to authorized local workspaces through filesystem and git tools, multimodal file inspection, and explicitly allowlisted named tasks, without exposing write, delete, or arbitrary-shell capabilities.

MCP server that pushes GitHub Actions CI/CD results and PR events into Claude Code sessions, enabling automatic investigation and remediation.

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.

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.

A self-hosted MCP server that gives ChatGPT full local machine access for coding tasks, including file editing, shell commands, git operations, and project exploration via 40+ MCP tools.

Enables ChatGPT to securely operate a single Windows development workspace via a local MCP server, offering file editing, Git status, static analysis, approved test/build, and limited ADB operations with audit logging.

MCP server that integrates with VS Code to enable file operations, git diffs, and line highlighting via MCP clients like Claude.

A lightweight MCP server that handles git operations on behalf of AI coding assistants, running as a local HTTP service without external network exposure by default.

Self-hosted MCP coding server and unified local Control Center for ChatGPT web, enabling file editing, command execution, Git operations, and optional upstream MCP tools with conversation access controls.

Enables AI assistants to securely inspect, modify, and manage local projects with trusted filesystem access, safe Git operations, controlled task execution, and developer runtime process management over stdio or HTTP.

Enables two people's Claude agents to hold a live conversation about the same project, using GitHub Issues as channels and Issue comments as messages. Each side can list channels, open new ones, send and read messages, and wait for the other's reply, while both users follow and join in directly on GitHub.

Enables a Notion MCP Agent to work as a local coding agent by exposing local files, shell, git, and patch-style editing over MCP, plus delegated long-running tasks via local Codex or Claude. It also supports managing local MCP services and Cloudflare tunnels through a native macOS console.

Enables ChatGPT web to safely read and modify only explicitly allowed local project files through OpenAI Secure MCP Tunnel, including git operations, file edits, and running project scripts, while enforcing strict security boundaries.

Enables MCP-compatible AI clients to connect to a Windows machine for file operations, PowerShell execution, Git inspection, task management, memory, and skills.

Enables two coding assistants to coordinate task creation, claiming, messages, and completion through a shared local workflow queue while using GitHub issues, branches, commits, and PRs as the source of truth.

A local MCP server that turns AI clients into power users of local git repositories, enabling clone, browse, search, and inspect code without burning API tokens.

A Multi-Agent Conversation Protocol Server for the GitHub API, auto-generated using AG2's MCP builder, allowing users to interact with GitHub services through natural language.

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