Developer Tools MCP servers

Help AI agents find and evaluate mature packages across 6 ecosystems instead of reinventing them.

Safety-first Kaggle MCP — confirm-gated destructive ops, submission budget, injection-fenced.

FAISS, call graph, AST, BM25 — 34 MCP tools for AI agents. 50-80% token reduction. Offline.

Validate design tokens for accessibility, scales, and design-system constraint consistency.

Extract a website’s design tokens (colors, type, spacing, shadows) as DESIGN.md, W3C, or CSS.

Fresh, source-verified docs for building MCP servers and Claude agents, for AI coding agents.

Distill AI coding sessions into weekly reports, ADRs and a knowledge graph - self-hosted

Deterministic layered code graph MCP server with framework overlays and SCIP interop.

Visual accessibility inspector. WCAG contrast, touch targets, heading audits, screenshots.

Synchronize Colab notebook files through Google Drive without executing notebook code.

MCP server for LLM-driven SUMO traffic simulation, scenario design, and result analysis.

AI code review for your AI assistant — review local changes, branch diffs, and patch files.

Go from natural language to verified finite state machines — topology bugs caught before code runs.

Automate Windows WPF apps from AI agents with semantic UIA selectors and FlaUI test generation.

AST-based semantic code search; results ship with their call graph (calls + callers).

Cross-platform MCP server for managing long-lived background processes from any MCP client

Let AI agents inspect, control, and debug real iOS, Android, desktop, and TV apps

Local codebase search for AI assistants via MCP. Requires Hawkeye and Hawkeye AI Bridge installed.

A Model Context Protocol (MCP) server for process management.

OSS license metadata + compatibility checker MCP server.

Personal RAG over your GitHub history (commits, code, reviews), served to Claude Code over MCP.

Connect your AI agent to anything — APIs, databases, and agents; read and write, auto-discovered.

Lightweight MCP server providing terminal access (SSH & local shells) for AI assistants.

Secure code execution sandbox for Claude — run Python, JavaScript, and shell commands

Operational memory for AI agents: code graph, session memory & guardrails. No context rot.

A powerful toolkit for coding, providing semantic retrieval and editing capabilities.

Local test execution and coverage summaries for onboarding agents.

An MCP server that fuses LLM contextual intelligence with procedural code reliability.