AI & Agents MCP Servers for Devin Desktop

Qantara (arched bridge): an MCP bridge that lets coding agents (Claude Code, Codex, Gemini) delegate tasks to each other.

Find your AI agent's likely failure mode, get runtime settings, and clarify ambiguous prompts.

Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.

Read-only tools over the Safer Agentic AI framework: 238 patterns + 14 heuristics.

Semantic router for MCP ecosystems - Discover, manage, and execute tools across multiple MCP servers with progressive disclosure

MCP server for semantic prompt framework - NLP-inspired adaptive reasoning engine for LLM orchestration

Universal prompt loader MCP server

MCP server for the Shinzo AI platform for agent orchestration and analytics

MCP server for translating Sinhala/Singlish commands into English technical prompts

Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.

MCP State Sidecar: durable state persistence for multi-agent AI workflows

MCP server for structured thinking framework - Step-by-step reasoning and systematic problem-solving for LLMs

Context Engineering Engine. Provides cognitive tools, memory structures, and agent patterns.

Local task classification for coding-agent model selection.

MCP server for The Agents — real-time AI agent visualization

A thinking tool MCP server for decomposing and organizing thoughts.

MCP Server for 6-stage Thinking Protocol Framework

MCP server for AInternet — DNS, identity and messaging for AI agents. Resolve .aint domains from Claude Code, Cursor, or any MCP client.

MCP server for TOON (Token-Oriented Object Notation) - Reduce LLM token usage by 50-70%

MCP server for Twake.ai: integrate your sovereign Digital Workplace with any MCP-compatible AI assistant

MCP server that creates and critiques plans using two-step Claude evaluation