What is required to use this server?
You need a Tugboat API key set as the `TUGBOAT_API_KEY` environment variable. The server also requires Node.js and npm for installation.
@Lullabot
Basic information
A Model Context Protocol (MCP) server for interacting with the Tugboat API.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"tugboat-mcp": {
"command": "node",
"args": [
"/path/to/tugboat-mcp/dist/index.js"
],
"env": {
"TUGBOAT_API_KEY": ""
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A Model Context Protocol (MCP) server for interacting with the Tugboat API. It allows AI assistants like Claude and Cursor to access and manipulate Tugboat resources—projects, previews, and repositories—through the standardized MCP interface.
Install by cloning the repository and running npm install && npm run build. Set the required environment variable TUGBOAT_API_KEY (and optionally TRANSPORT_TYPE, PORT, TUGBOAT_API_URL). Configure the server as an MCP tool in Claude Desktop or Cursor using the provided JSON/command template, or run it directly with HTTP transport for API access.
You need a Tugboat API key set as the `TUGBOAT_API_KEY` environment variable. The server also requires Node.js and npm for installation.
The server supports both stdio (default) and HTTP transports. The transport type is set via the `TRANSPORT_TYPE` environment variable. Stdio is used by Claude Desktop and Cursor; HTTP allows direct API calls.
Send a POST request to `http://localhost:3000/auth/login` to receive a token, then include that token as a Bearer token in the `Authorization` header for subsequent MCP requests.
Yes. Configure the server in `claude_desktop_config.json` with the command and `TUGBOAT_API_KEY` environment variable. After restarting Claude Desktop, the tool will appear and can be used via natural language prompts.
Resources include projects, previews, repositories, and logs (e.g., `tugboat://projects`, `tugboat://preview/{id}/logs`). Tools cover CRUD operations for projects, previews, and repositories, plus search, build, clone, and statistics retrieval.
Hindsight: Agent Memory That Learns
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
MCP Toolbox for Databases is an open source MCP server for databases.
A curated list of references for MLOps
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
Comments