nanobot
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
MCP server by Zapier · vendor-hosted · maintained
Official Zapier-hosted MCP connect endpoint. Point any Streamable HTTP client at mcp.zapier.com and authenticate with OAuth or a connection token to run Zapier actions.
Choose your AI client and copy the config.
Remote MCP — add to claude_desktop_config.json (or Connectors). Clients without native remote support can use the mcp-remote bridge below. Setup guide
{
"mcpServers": {
"zapier": {
"url": "https://mcp.zapier.com/api/v1/connect"
}
}
}stdio bridge (mcp-remote):
{
"mcpServers": {
"zapier": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.zapier.com/api/v1/connect"
]
}
}
}Add to ~/.cursor/mcp.json or .cursor/mcp.json, then complete OAuth when prompted. Setup guide
{
"mcpServers": {
"zapier": {
"url": "https://mcp.zapier.com/api/v1/connect"
}
}
}Add to .vscode/mcp.json (HTTP transport). Setup guide
{
"servers": {
"zapier": {
"type": "http",
"url": "https://mcp.zapier.com/api/v1/connect"
}
}
}Cascade → MCP servers → Add custom server. Setup guide
{
"mcpServers": {
"zapier": {
"url": "https://mcp.zapier.com/api/v1/connect"
}
}
}Run in your terminal, then /mcp to authenticate: Setup guide
claude mcp add --transport http zapier https://mcp.zapier.com/api/v1/connectCLI or add to ~/.codex/config.toml. Setup guide
codex mcp add zapier --url https://mcp.zapier.com/api/v1/connect[mcp_servers.zapier]
url = "https://mcp.zapier.com/api/v1/connect"Use the mcp-remote bridge if the client is stdio-only. Setup guide
{
"mcpServers": {
"zapier": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.zapier.com/api/v1/connect"
]
}
}
}ChatGPT web needs a remote HTTPS MCP URL (Plugins → Add custom MCP server). Setup guide
https://mcp.zapier.com/api/v1/connectVendor-hosted Streamable HTTP endpoint (OAuth on first connect):
https://mcp.zapier.com/api/v1/connectUltra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
Open-source agentic workspace enterprises can make their own. Connect the systems you already run — 100+ integrations, MCP, chat tools, apps, browser, local files — with shared memory. Any agent (Claude Code, Codex), any model, or BYOK. Set up in clicks, not months. Local-first: your data never leaves your machines.
Build effective agents using Model Context Protocol and simple workflow patterns