AI & Agents MCP Servers for Devin Desktop

Prompt-driven dialectical reasoning and autocoding for LLMs (thesis -> antithesis -> synthesis)

Lossless skim-then-expand reading of big files, repos, and command output with far fewer tokens

MCP server for Help an Agent — consult real humans for emotional, social, ethical, or cultural validation

HumanAgent MCP Server - Let AI agents hire humans for real-world tasks

Block prompt injection, evasive spacing, and obscene content before it reaches your LLM.

A MCP server for interactive user questions with native UI

Enhanced MCP Server for interactive communication between LLMs and users with custom sound notifications, approval workflows, clipboard

MCP server for efficiently exploring large JSON files

Judge QA for agents — measures whether your LLM judge agrees with humans, drifted between runs, or is biased, before you ship the number

A curated Kimi Coding Plan usage monitor with aesthetic CLI and MCP server.

AI agent knowledge marketplace. Discover, purchase, and retrieve human expertise via x402 on Solana.

Fork of sequential-thinking MCP server with native Semantic Plausibility Gating

MCP server for Labradoc — exposes files, email, tasks, user stats, and integrations as MCP tools

MCP server for building and modifying Langflow flows via LLM agents

MCP Server for Leaflet — AI agents control maps via stdio + WebSocket

A lazy-loading MCP proxy that cuts your agent's startup context from tens of thousands of tokens to a few hundred — it exposes upstream

MCP server for on-demand human-in-the-loop interactions via Slack - get human input when AI agents are stuck or facing critical decisions

Verify AI agent communication with session types and formal proofs

MCP server for LoopIn — human-in-the-loop interrupt API for AI agents

MCP server exposing the full Manus API v2 surface to Claude Code

MCP server providing verified math & logic tools for small LLMs (Mistral, Llama, DeepSeek)