MCP server for MDMA — exposes spec, prompts, docs, and package metadata to AI assistants.
Loading the directory
Loading the directory
Claude Desktop reads mcpServers from claude_desktop_config.json. Restart the app after saving.
claude_desktop_config.json at the path for your OS.~/Library/Application Support/Claude/claude_desktop_config.json~/.config/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonEvery server page builds a ready-to-paste JSON config for Claude Desktop.
Servers that can be installed in this client.
MCP server for MDMA — exposes spec, prompts, docs, and package metadata to AI assistants.
Comments pinned on a website, as a queue your coding agent takes, fixes and resolves.
ABAP development from Claude and other MCP hosts: source, transports, tests, ATC, debugger

Every CrowdStrike Falcon MSP operation, plus a Flight-Control-aware local store that answers
Cloud DevOps analysis with guarded Git, infrastructure, cloud and observability operations.
Guardrail for AI agents on SQL Server: statement blocking, optional read-only mode and an audit log.
Use this MCP server to Sega Retro, every Sega game, console, and unreleased hardware. Tools...
Local-first Sui DeFi evidence and review for AI clients before wallet signing.
Disclose AI authorship of code per the ACO standard — tools for AI coding agents.
What a role really pays, including markets where the employer publishes no range.
OWASP MCP08 audit/telemetry gaps: missing tool-call logs, raw args in logs, disabled audit
Living economy for AI agents — Conway physics, energy currency, marketplace, reputation.
Saves AI coding-agent context by giving exact code instead of whole files, from a local graph.
Find available appointments on public SuperSaaS resource schedules
Scans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure
Mesh (STL/OBJ/PLY) to editable STEP, CadQuery or OpenSCAD: primitive fitting, fidelity report
Read available slots from a public OnlineAfspraken widget URL without an account.
Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.
Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
Plan, write and publish SEO articles on your own site, and track your Google and AI search traffic.
DEPRECATED: no live endpoint (api.caf.io does not resolve)
Parse, lint, format, render, and migrate Carve documents through MCP.
Swiss federal law, consultations (Fedlex) & TERMDAT terminology (LINDAS) via SPARQL