Developer Tools MCP servers

Code graph and project memory for coding agents, cited to exact files and lines, on your machine.

Finds UI drift in React apps (buttons, cards, colors, spacing) and gives your agent each fix

Evidence-based GSoC preparation: organizations, repositories, free beginner issues, proposals.

A sandboxed, agentic workspace providing secure filesystem, bash, and uv-powered Python execution.

Production-grade MCP server for KiCad EDA—PCB design, DRC, simulation, BOM, DFM, and manufacturing.

Architecture diagrams with official AWS, Azure, GCP and Kubernetes icons, to SVG, PNG and draw.io

Catches palette colors, native elements and APIs your design system lacks in agent-written React.

Structural code-quality tools for AI coding agents.

Local memory, a work tracker and a shell-command guard shared by coding agents on one machine.

Read-only checks of which git name, email and SSH key a repository uses, and why.

Offline deterministic engineering-trust certificates for repositories, with no telemetry.

Bridge AI coding hosts to cursor-agent over the Agent Client Protocol.

Bridge AI coding hosts to the OpenAI Codex CLI for delegated implementation.

Decodes MsgPack (LsMsgPack schemas, type ids) as text and reads it from variables while debugging.

Lets AI agents drive a real terminal: type, press keys, click, read the screen, take screenshots.

Develop, test, analyze, and operate SAP ABAP systems through ADT from AI coding agents.

Code search for coding agents: ranked, exact excerpts with line numbers.

Kotlin/Java library sources, public API and KDoc from the real Maven sources jar, for AI agents

Bring Visual Studio-style C# fixes and refactorings to your AI agent with local Roslyn Code Actions.

Local dependency graph: callers, entry points and file:line evidence for what a change affects.

Python capability compiler: read-only analysis, experiment history/comparison and exposure planning.

Serves Oracle Forms module content (.fmb/.mmb/.pll/.olb) from a directory to MCP clients.

Generates tests from acceptance criteria, then converges code with an agent that never sees them.

Create, update, review, and resolve visual tests with Applitools Eyes across any supported SDK.

Background Windows desktop for AI agents: native GUI automation, screenshots and app testing.

Extract file and directory paths from config files and code, with their kind and position.

Phone-first OpenCode MCP for trusted devices: run, build, deploy, and manage endpoint-local tools.

MCP server for Moodle plugin development: structural context of a Moodle install for AI agents.