Your primary AI is confident — but confidence isn't correctness. A second model, with no stake in the first one's answer, catches what it missed.
Your primary AI is confident — but confidence isn't correctness. A second model, with no stake in the first one's answer, catches what it missed.
agy) >=1.1.5 —ask-gemini — @ask-llm/gemini-mcpask-gemini-edit — @ask-llm/gemini-mcpfetch-chunk — @ask-llm/gemini-mcpask-codex — @ask-llm/codex-mcpask-claude — @ask-llm/claude-mcpask-ollama — @ask-llm/ollama-mcpask-antigravity — @ask-llm/antigravity-mcpask-llm — @ask-llm/mcpmulti-llm — @ask-llm/mcpget-usage-stats — alldiagnose — @ask-llm/mcpping — allCompare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| ask-gemini | @ask-llm/gemini-mcp |
| ask-gemini-edit | @ask-llm/gemini-mcp |
| fetch-chunk | @ask-llm/gemini-mcp |
| ask-codex | @ask-llm/codex-mcp |
| ask-claude | @ask-llm/claude-mcp |
| ask-ollama | @ask-llm/ollama-mcp |
| ask-antigravity | @ask-llm/antigravity-mcp |
| ask-llm | @ask-llm/mcp |
| multi-llm | @ask-llm/mcp |
| get-usage-stats | all |
| diagnose | @ask-llm/mcp |
| ping | all |
{
"mcpServers": {
"ask-gemini": {
"command": "npx",
"args": ["-y", "@ask-llm/mcp"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
agy) >=1.1.5 —The original Chromium automation reference server — simple, screenshot-driven browser control.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Automates browsers and APIs, enabling Large Language Models (LLMs) to interact with web pages for tasks like screenshot capture and JavaScript
Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.