AI & Agents MCP Servers for Devin Desktop

Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.

Any model, one interface — the three.ws multi-provider LLM router over MCP. Discover available providers/models (Claude, GPT-4o, Qwen

Turn any OpenAPI spec or API docs link into a hosted MCP server. Free Kaiva Bridge account.

Coding agents read frozen requirements, report progress, and submit delivery evidence.

Search a curated directory of AI tools, AI agents and MCP servers by task, pricing and platform.

Train, test, install and review a website AI agent (CAAC Go) from any MCP client.

LLM caching proxy (x402 USDC on Base) - exact + semantic cache. Free health.

The infrastructure for the AI economy: primitives for inference, agents, and decisions.

Image, video, music and text generation across 100+ models through one endpoint.

Learn and adopt the Capability Host Protocol — the agentic web's open evidence layer.

Find and try paid AI agent skills for security, on-chain data, code, markets, research and news.

Anthropic Claude Messages API MCP server — chat, vision, web search, extended thinking

Claude Schema Output Agent

MCP Gateway: wrap any MCP server with cold-start retries, uptime SLA, and per-execution MPP billing.

AI agent hosting platform: 37+ connectors, 181 tools, BYOK vault, marketplace.

Run 70+ AI models and 50+ tools on CNAPS Studio in natural language — Claude, n8n, or Zapier.

Codex reset tracker: usage-limit reset announcements from @thsottiaux on X. Read-only, no key.

Read-only discovery of AI agents in your Communicate workspace.

Connect AI agents to 1000+ apps with managed authentication and tool-calling.

OpenAI-compatible multi-model inference via ComputeFlux (Polkadot testnet, TEE-verifiable). stdio.

Build, test, deploy, and operate Connic agents.