Loading…
AI task cockpit where a sandboxed autonomous agent completes tasks and pauses for approval before irreversible actions.
Review before connecting
The findings on this server are worth reviewing before you connect an agent to it.
Scanned 6 days ago
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The RadTask MCP server exposes 3 tools, focused primarily on general-purpose capabilities. Its published description reads: "AI task cockpit where a sandboxed autonomous agent completes tasks and pauses for approval before irreversible actions". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates RadTask C- — the findings are worth reviewing before you connect an agent to it. Its most notable findings include "Cross-tool shadowing" and "No authorization on a public remote server". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check RadTask's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add RadTask to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://radtask.ai/api/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Add a task to the user's RadTask cockpit. Use this to capture anything the user wants done or tracked.
List the user's RadTask tasks, optionally filtered by status.
Mark a RadTask task done by its id (from list_tasks).
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: complete_task
A tool description tries to alter the model’s use of another tool.
by its id (from list_tasks).RecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
Validates ZUGFeRD, Factur-X, and XRechnung e-invoices against EN 16931 with correction suggestions.
Tracks US tariff and trade-action changes from Federal Register documents and exposes them through an API for AI agents.
Instant rug-check for any EVM or Solana token, distilled to one clear 0-10 risk verdict.
Provides access to Bible translations, books, chapters, verses, and search functionality.
Remote-first MCP adapter for emitting Settlement Attestation Receipts; not a verifier.
Risk-ranked registry of AI tools for enterprise governance, enabling lookup of tool risk and shadow AI domain detection.