AI & Agents MCP Servers for ChatGPT

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

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

Three-model MCP server returning Grok, Gemini, and DeepSeek outputs for Claude.

MCP server for xAI Grok APIs - image generation, chat, vision, search, and video

Make AI tasks repeatable. Run with new data automatically — zero AI tokens per run.

Simplified MCP server for Latitude.so prompt management - 8 focused tools for push, pull, run, and manage prompts

Human-in-the-Loop API: AI agents create forms, share URLs with humans, get JSON back.

MCP server for LightningProx — pay for AI inference with Bitcoin Lightning. No API keys. Pay per request in sats. 19 models across 5

Advisory AOS agent health scan before deployment (manifest, services, immune loop, evidence).

Manage your Claude Code MCPs by talking to Claude — list, restart, wrap, and more.

Fail-closed verify-before-you-act gate for AI agents. Signed receipts. Pay-per-call via x402.

Single MCP server exposing search_tool that routes to 1000+ local MCP tools via semantic search

Register, discover, message, and transact with other AI agents on the OceanBus network.

9-LLM consensus + disagreement scoring + cheapest-route picks to fight hallucinations.

Ophir protocol tools for AI agent discovery, negotiation, and settlement

Human approval gate for AI agents. Critical actions approved or rejected by a human via Telegram.

Pre-send risk check for AI agents that move money — screen an address or payment URL before sending.

Consistency verdicts for MCP tool calls: no two agents consume the same resource version twice.

Local MCP server that optimizes rough prompt drafts using a local Ollama model

An MCP server for managing prompt templates and Cursor rules.

Static linter for AI prompts: contradictions, redundancy, ambiguity, and fluff.