About radtask-mcp
radtask-mcp connects AI clients to the RadTask task manager, where an agent carries out tasks and holds irreversible actions for user approval. It supports task creation, tracking, and completion.
Key features
- 01Create tasks from plain-language requests
- 02List tasks by status
- 03Mark tasks as complete
- 04Hold irreversible actions for approval
Use cases
- 01Send AI-created work to the RadTask cockpit
- 02Track tasks through completion
- 03Require approval before sending or deleting
MCP support
Exposes task creation, listing, and completion tools through a Streamable HTTP MCP server. Tasks are routed to the user's RadTask cockpit.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://radtask.ai/api/mcpclaude mcp add --transport http dougsureel-tech-radtask https://radtask.ai/api/mcp{"mcpServers":{"dougsureel-tech-radtask":{"type":"http","url":"https://radtask.ai/api/mcp"}}}Open in Cursor{"servers":{"dougsureel-tech-radtask":{"type":"http","url":"https://radtask.ai/api/mcp"}}}Open in VS Code{"mcpServers":{"dougsureel-tech-radtask":{"type":"http","url":"https://radtask.ai/api/mcp"}}}{"mcpServers":{"dougsureel-tech-radtask":{"serverUrl":"https://radtask.ai/api/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
3| Parameter | Type | Required | Description |
|---|---|---|---|
| title | string | Yes | The task in plain English |
| project | string | No | Optional project to group it under |
Details
From the project READMERadTask 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_TOKEN
Get 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
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.