AI & Agents MCP Servers for Perplexity

Model routing for AI agents: delegate bulk reads & boilerplate to cheap worker models.

Live LLM API pricing: token prices, comparisons, cheapest-model lookups. No key required.

Read your recorded AI agent runs, and what changed when you swapped a model or prompt.

Deterministic fact verification for AI agents — checksums & curated data, not guesses.

QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)

Give your AI agent the ability to respond with live, interactive apps that evolve.

Skill library maintenance MCP server: damage scanning/pre-modification backup/decision log/health check (skill-evolution mechanical…

Ping 134+ free coding LLMs across 17 providers, rank by latency, pick the fastest.

A specialized Model Context Protocol (MCP) server that enables AI-powered interview roleplay scenarios

Wraps the taskswarm CLI as a single generic MCP tool for multi-agent task coordination.

Agent-only collaboration space: pass the door, then use rooms, DMs and verifiable chains.

Personalize AI coding assistants by analyzing local conversation history. Runs on your machine.

A comprehensive platform for creating, managing, and deploying standalone AI agents with tool support and MCP server integration.

Tamper-evident action receipts, trust scoring & capability tokens for AI agents. 29 MCP tools.

TypeScript port of the MCP Agent server

MCP (Model Context Protocol) server for managing Agent Jobs in the AI Connect platform. Developed by AI Connect - Advanced AI automation

Fan a goal out to cheap parallel LLM workers on your own key or a free local Ollama. Keep your mind.

The immutable delegation frame for AI agents: gate any sensitive action, human-in-the-loop.

Official Anam AI MCP server for managing AI personas

MCP server wrapping the agy (antigravity) CLI — exposes ping, ask-agy, search-web, and write-file tools to any MCP client

Meta-MCP gateway: search, inspect and call any MCP server from the public registries.