FlowDot runs on your own machine — the client starts it, so there is no endpoint to ping. 598 installs a week from npm. Last commit 4 Oct 2026.
Build and run AI workflows, apps, toolkits and knowledge bases on FlowDot from any MCP client.
We read the source, 6 d ago · rules ccca72095570
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
pty.spawn(shell, args, { name: opts.name, cols: opts.cols, rows: opts.rows, cwd: opts.cwd, env: opts.env }) as never;
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-server -- npx -y @flowdot.ai/mcp-server
{
"mcpServers": {
"mcp-server": {
"args": [
"-y",
"@flowdot.ai/mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-server]
command = "npx"
args = ["-y", "@flowdot.ai/mcp-server"]
{
"mcpServers": {
"mcp-server": {
"args": [
"-y",
"@flowdot.ai/mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-server": {
"args": [
"-y",
"@flowdot.ai/mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
FLOWDOT_API_TOKEN (Your FlowDot MCP token (starts with fd_mcp_). Create one free at https://flowdot.ai/mcp), FLOWDOT_HUB_URL (FlowDot Hub URL. Defaults to https://flowdot.ai).
The author declared them in the registry entry; get the values from the project itself.
Read and edit your Acorn Reply knowledge base from any MCP client.
Build, run and publish Workbench flows, tasks, shims and knowledge bases.
Run the Intelliverse platform from any agent: apps, API keys, knowledge bases, email, media, chat.
Build and run grounded business agents over MCP: agents, knowledge bases, skills, Storylines.
MCP server exposing Dify knowledge base retrieval to Cursor and other MCP clients
ComfyUI MCP server: knowledge base, workflow builder, real-time execution, models, plugins.
Read and write your team's shared, AI-readable wiki from any MCP client.
Knowledge base MCP for AI agents on iknow.dev. Search, read, and maintain via OAuth.
Answers built from our own checks of this server.