AI & Agents MCP Servers for Perplexity

MCP server that refines and improves user prompts for AI-optimal readability

Run local prompt regression checks from prompt-response logs in AI coding assistants.

Desktop MCP server for AI agents - screenshots, clicks, typing, and more on macOS and Windows

Python client for SLM Mesh — peer-to-peer communication for AI coding agents.

Wraps the slop-eval CLI as a single generic MCP tool for genericness scoring of AI UI output.

MCP server that checkpoints long agent tasks: roll back to any step, resume in a new session.

MCP Server for ThinkPrompt - Prompt Management System with Multi-Workspace Support

Track LLM token costs across Claude, GPT and Gemini. MCP server + CLI dashboard with optimization hints.

Verifies token/cost savings claimed by AI context-reduction proxies via MCP tools.

Local stdio MCP server for the AEGIS governance client. The hosted evaluation service is offline.

MCP server for Google Vertex AI — 180+ tools covering datasets, endpoints, models, indexes, featurestores, pipelines, tensorboards, and more

Public benchmark where agents submit Q&A answers and get scored on a leaderboard.

Admission gate for AI agents: submit a step, get admit/hold/reject vs your constitution.

Hand a human a rich interactive UI by URL and get structured data back, from any MCP client.

CLI-driven, OpenCode-centered experiment runner: vary system prompt / model / task prompt, run isolated in Docker, capture and compare

Planning and orchestration for AI-driven software development

Shared versioned state for multi-agent AI workflows

AgentPact MCP server — thin transport shell over @agentpactai/live-tools.

MCP server for Anthropic's Claude Fable, Opus 5, and multi-model reasoning councils.

MCP server enabling LLMs to consult with Google's Gemini models for additional insights and alternative perspectives

A powerful MCP server providing access to multiple AI models (Grok, Gemini, Kimi, Qwen, GLM) through OpenRouter. Perfect for Cursor, Claude