io.github.dougsureel-tech/radtask-mcp
AI task cockpit: an agent does your tasks and asks before anything irreversible.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
claude mcp add --transport http radtask-mcp 'https://radtask.ai/api/mcp'{
"mcpServers": {
"radtask-mcp": {
"type": "http",
"url": "https://radtask.ai/api/mcp"
}
}
}Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
RadTask MCP Server
Connect any AI to your task cockpit. RadTask is an AI task manager whose agent actually does the task — and asks first before anything irreversible. It runs a live MCP (Model Context Protocol) server, so Claude, ChatGPT, Cursor, or your own agent can create and track tasks that land in the user's RadTask cockpit, where a safe autonomous agent runs them.
Private beta. A tool with a safety design — not a guarantee.
Connect
Endpoint (Streamable HTTP, JSON-RPC 2.0):
https://radtask.ai/api/mcp?token=YOUR_TOKENGet your private token at radtask.ai/connect. The token is your cockpit's namespace — tasks an AI adds appear in your RadTask.
Claude Desktop / Cursor
{
"mcpServers": {
"radtask": { "type": "http", "url": "https://radtask.ai/api/mcp?token=YOUR_TOKEN" }
}
}Tools
| Tool | What it does |
|---|---|
create_task | Capture a task in plain English (optional project) |
list_tasks | List tasks, optionally filtered by status |
complete_task | Mark a task done by id |
Why RadTask is different
Most "task manager" MCP servers are queues — they track what an AI should do. RadTask does the task: a real agent researches, drafts, writes documents, and schedules in a sandbox — and a deterministic risk classifier holds only the irreversible steps (sending, spending, deleting, publishing) for the user's one-tap approval.
The safety posture is published and machine-verifiable:
- Safety contract: https://radtask.ai/.well-known/agent-safety.json
- MCP manifest: https://radtask.ai/.well-known/mcp.json
- For AI agents: https://radtask.ai/for-agents
- llms.txt: https://radtask.ai/llms.txt
Design goal: zero unsupervised destructive actions. Irreversible actions are always held for a human.
Links
- Product: https://radtask.ai
- MCP page: https://radtask.ai/mcp
- A Sureel product · part of the Rad family (RadMail · RadTask · RadHealth)
License
MIT © Sureel
Frequently asked questions
What is io.github.dougsureel-tech/radtask-mcp?
AI task cockpit: an agent does your tasks and asks before anything irreversible.
How do I install io.github.dougsureel-tech/radtask-mcp?
It runs as a remote server. In Claude Code: claude mcp add --transport http radtask-mcp 'https://radtask.ai/api/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.
Does io.github.dougsureel-tech/radtask-mcp need an API key?
Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.
Is io.github.dougsureel-tech/radtask-mcp open source?
Yes. Its code is on GitHub under the MIT license.
Who maintains io.github.dougsureel-tech/radtask-mcp?
It is published by dougsureel-tech. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.