"Creating custom experimental images in Docker" matching MCP servers:

Provides integration with GitLab repositories to manage files, issues, merge requests, and branches through the Model Context Protocol. This implementation includes specific fixes for schema validation issues found in standard GitLab MCP servers.

Enables AI agents to perform full CRUD operations on GitHub, including repositories, issues, pull requests, branches, comments, reviews, and merges through the Model Context Protocol.

A modular monolith MCP server connecting multiple providers (Redash, PostgreSQL, GitHub) with unified permission, security, and auditing, enabling secure data access and tool execution.

An experimental MCP server offering calculator, GitHub repository fetching, a movie database resource, and JavaScript code review capabilities. Designed for learning and compatible with Cursor and Claude Desktop.

Enables AI coding assistants, agents, and pair programmers to read, write, and orchestrate GitLab SaaS or self-hosted instances through 218 tools spanning merge requests, issues, pipelines, runners, repositories, and more, with configurable safety tiers and multiple transport modes.

Enables Claude and other MCP clients to read and write GitHub repositories, pull requests, issues, files, branches, commits, releases, and more using a personal access token without OAuth.

A custom server implementation that allows AI assistants to interact with GitLab repositories, providing capabilities for searching, fetching files, creating/updating content, and managing issues and merge requests.

Provides tools for interacting with the GitLab API, enabling AI assistants to search repositories, manage issues, create branches, and more through natural language commands.

Enables direct GitHub operations through Claude and Cursor, including repository management, branch creation, issue tracking, and pull request management. Provides seamless integration with GitHub API for comprehensive project workflow automation.

MCP server that analyzes git activity from a repository mounted at /repo, exposing an SSE interface and health check endpoint.

Provides MCP tools for GitHub code search, Jira sprint status, pull request risk analysis, and project metrics, enabling agentic workflows for developer productivity.

An MCP server for creating, validating, and formatting Git commits with emojis following the conventional commit standard.

A Model Context Protocol server that enables AI assistants to interact with Azure DevOps services, allowing users to query work items with plans to support creating/updating items, managing pipelines, handling pull requests, and administering sprints and branch policies.

An MCP server that reads public GitHub Projects v2 boards (including item-level data like status and custom fields) without authentication, using official APIs and fallback methods for user-owned projects.

MCP server for creating, versioning, retrieving, and publishing HTML presentations, using git as the source of truth and Google Apps Script for deployment.

An MCP server that enables AI assistants to interact with GitHub via a fine-grained personal access token — pushing commits, managing branches, opening and merging PRs, creating issues, and reading repositories. It runs locally with no telemetry and supports a read-only mode.

Quilt gives every AI agent line-level authorship in a shared Git checkout, so multiple agents work in one repo, and each commits only its own lines, with symbol-level claims that block collisions before any bytes change.

MCP server for Google Jules enabling LLMs to create coding sessions with automatic pull request creation from issues or custom prompts.

Enables detection and resolution of Git merge conflicts in repositories through MCP, providing tools to identify conflicting files and assist with conflict resolution workflows.

Local MCP server for safe GitHub developer workflows. Enables pulling main, creating feature branches, pushing them, and opening ready-for-review pull requests via tools like github_create_feature_branch and github_create_pull_request.