AI & Agents MCP Servers for Perplexity

Rust MCP gateway with Code Mode, authentication, setup, logs, CLI, HTTP API, and operator web UI.

MCP chaos-testing toolkit. Default: simulated demo. Configure proxy mode to test a real agent.

Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.

Personal Model Recommender — find the best model for YOUR tasks

Model Context Protocol (stdio) server for Homespun: lets any MCP client (Claude Desktop, Cursor, …) deploy a multi-user web app with

Remote-control Claude Code, plus PandaNote notes, AI model configs & scheduled tasks.

Search and load AI datasets, prompts and few-shot contexts from the ContexteTech catalogue.

Reasoning orchestration MCP - Tree of Thoughts with multi-agent evaluation. Fork of Anthropic's sequential-thinking with string coercion

One group chat for your AI coding agents: Claude Code and Cursor talk to each other and to you.

Run AI magic workflows from glif.app

Journals every MCP tool call with secrets redacted; with a policy, holds risky calls for approval

Connect your AI to human workers. Get paid to help AI.

MCP server for Linux desktop GUI automation on KDE Plasma 6 Wayland — virtual testing and live desktop automation

Local 2B and 0.8B decision models: calibrated yes/no, choice and score answers for your agent.

Gamified Personal Prompt Coach — Duolingo for AI prompting with levels, streaks, and badges

Compute price oracle for AI agents — compare pricing across 8 providers in real time.

BridgeNode — x402 pay-per-request AI inference. OpenAI-compatible API + MCP, Solana USDC, gas-free.

MCP server for local LLMs — connects to LM Studio or any OpenAI-compatible endpoint

The small print of MCP servers, skills and plugins, hashed, diffed and graded, from the record.

Work-queue kernel for AI coding agents: dependencies, worktree isolation, quality gates, recovery

Cinematic website prompts as slash commands, tuned for Lovable, Bolt, Cursor and Claude.