MCP QUEEN
io.github.dougsureel-tech/radtask-mcp A
AI task cockpit: an agent does your tasks and asks before anything irreversible.
Dev & Codev0.1.0streamable-httpradtask.ai repository
Grade evidence — probed 2026-07-14 00:30 UTC
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 185ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo RadTask@0.1.0 |
| tooling | 35 / 35 | tools/list OK: 3 tools e.g. "create_task"; 3/3 described, 3/3 fully-typed schemas, median description 61 chars |
| latency | 10 / 10 | initialize round-trip 185ms |
| provenance | 15 / 15 | description present; repository linked; version 0.1.0; namespace io.github.dougsureel-tech matches endpoint/repo |
Score 100/100 · latency 185ms · 3 tools · auth: open
Connect your agent
Claude Code:
claude mcp add --transport http radtask-mcp https://radtask.ai/api/mcp
Generic MCP client config:
{ "mcpServers": { "radtask-mcp": { "type": "http", "url": "https://radtask.ai/api/mcp" } } }
MCP Queen is a graded index, not a middleman — your agent connects directly to the server above. Check the grade and evidence first; that's the point.
Share this server: permalink https://mcpqueen.com/s/io.github.dougsureel-tech/radtask-mcp · referral link https://mcpqueen.com/go/io.github.dougsureel-tech/radtask-mcp (counts as “routed via the queen”).
Own this server? Embed your grade badge
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/io.github.dougsureel-tech/radtask-mcp)
Think the grade is wrong? Fix the finding the evidence shows, then the next probe cycle picks it up automatically (full cycle ≈ 3 days) — or open a dispute via the MCP endpoint.
Queen Watch
Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.
Probe history
| When (UTC) | Grade | Score | Latency |
|---|---|---|---|
| 2026-07-14 00:30 | A | 100 | 185ms |