AI & Agents MCP Servers for Perplexity

MCP server for Pretty Prompt — browse and save your prompt library

A simple MCP Server to manage prompts based on tasknames

Rubric-based technical answer feedback for AI agents; human review required.

Optimizing compiler for agent tools: many MCP servers or REST APIs in, one lean endpoint out.

Agent-native Tychi wallet MCP — onboard, status, chat, reset. Self-custody keys local; brain runs agent logic. Pin 1.0.0-beta.8.

WormXGPT — Unfiltered Chaos CLI. Multi-provider AI chat with 100+ tools, MCP integration, auto-fallback, multi-agent orchestration. No

Lints a Hugging Face model card against the Hub metadata spec and the EU AI Act general-purpose AI d

Wrap any korg:introspect@v1-aware binary as a Claude Code tool, honoring declared side-effects.

AAIF-verified modern MCP setup optimised to the 2026-07-28 model (BETTER textbook).

Wraps any MCP server: identical write-tool calls run once, and every tool call is audit-logged.

Stdio MCP server for Cursor, Claude Code, and other clients — route prompts to Gemini, ChatGPT, Claude, DeepSeek & Kimi via browser

⚡ MCP server aiming to free LLMs with enhancement prompts. Inspired by elder-plinius' L1B3RT4S.

Add human approval to AI agent workflows through cQnce authorization tools.

RunAPI MCP server for Runway Aleph: query historical tasks.

Reads your companion chatbot's system prompt against California SB 243, New York GBL Article 47, Ill

Reads .mcp.json / .vscode/mcp.json / claude_desktop_config.json while you edit it and marks the line

Provider-neutral OpenDeepThink reasoning server: generate, judge, rank, mutate.

MCP server caching expensive LLM responses: HTTP-style freshness plus semantic recall.

MCP server for GigaChat — AI chat, embeddings, image generation (Russia)

The capstone of the Grand Line stack — collect every tool to reveal the One Piece.

Look up independent trust ratings and security, maintenance, and adoption evidence for MCP servers.