Workflow is listed as active in the registry but did not answer our last check. Last commit 7 Nov 2026.
Create, browse, remix, collaborate on, and run durable AI workflow nodes from MCP hosts.
What changed 1
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 28 September 2026. No other catalogue keeps this.
What the code does
We read the source, 3 h ago · rules 995398eba69f
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
"/dev/tcp/",
self._run("mkfs.xfs", "-f", "-p", str(prototype), str(stage))
".aws/credentials",
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.
subprocess.run(
doc = yaml.load(text, Loader=_UniqueLoader)
def exec(
execFileSync(process.execPath, [WRANGLER, "types", ...(out === undefined ? [] : [out]),
".aws/credentials",
_PASTE_SITES = ("glot.io", "pastebin.com", "paste.rs", "termbin.com", "ix.io", "0x0.st")
RUN curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \
max_bytes=resolve_ceiling(dict(os.environ)) - CEILING_HEADROOM_BYTES,
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
path = os.path.join(proc_root, pid, "environ")
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found things in this code
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Workflow and you get told the day something new turns up.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.
claude mcp add workflow-universe-server --transport http https://tinyassets.io/mcp-directoryhttps://tinyassets.io/mcp-directory[mcp_servers.workflow-universe-server]
url = "https://tinyassets.io/mcp-directory"{
"mcpServers": {
"workflow-universe-server": {
"url": "https://tinyassets.io/mcp-directory"
}
}
}{
"servers": {
"workflow-universe-server": {
"type": "http",
"url": "https://tinyassets.io/mcp-directory"
}
}
}Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://tinyassets.io/mcp-directory | streamable-http | answering | 131 ms | 1 min ago |
Alternatives to Workflow
same job, measured the same wayBuild, test, publish, and run Kovca workflows from AI agents over remote MCP.
Build and run AI workflows, apps, toolkits and knowledge bases on FlowDot from any MCP client.
Create, test, publish, and manage Dreamlit notification workflows from AI clients.
Search, read, create, and organize Workflowy nodes with breadcrumb context.
Build and run visual creative-production workflows from your AI agent.
Build and run AI workflows, agents, data tables and 1000+ API integrations from any MCP client.
Resumable browser, API and MCP workflows for AI agents. Verify CSV/Excel batches locally.
Create designs, manage assets, and automate design generation from external workflows
Workflow — questions
Answers built from our own checks of this server.