io.github.RudrenduPaul/deskcertai

deskcert

Verified · 20 days ago

Evaluates whether an AI agent is safe to operate internal web apps via an MCP run_suite tool.

Install

claude mcp add deskcert -- uvx deskcert-cli

Our take

DeskCert evaluates whether an AI agent is safe to operate internal web applications through a `run_suite` style assessment. It is for teams experimenting with browser-operating agents who need a structured safety gate before broader deployment. That is a meaningful niche, but it is a specialized evaluation tool with limited public maturity signals and likely requires careful validation before being trusted in production.

reviewed by hand · 2026-08-11

Something wrong or dead here? Report it

Verification record

last verified
20 days ago
github stars
0
last commit
23 days ago
archived
no
license
Apache-2.0
in registry since
2026-08-11

github.com/RudrenduPaul/DeskCert-CLI

More in ai

browse all →
reaai

REA

Verified · 23 days ago

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

hand-reviewed291k stars232k dl/wkchecked 23 days ago

claude-flowai

claude-flow

Verified · 2 mo ago

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

hand-reviewed73k stars19k dl/wkchecked 2 mo ago

tldrawai

tldraw

Verified · 2 mo ago

Draw and visually collaborate with your agents on tldraw's canvas.

hand-reviewed50k starschecked 2 mo ago

codebase-memory-mcpai

Codebase Memory

Verified · 43 days ago

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

hand-reviewed45k stars12k dl/wkchecked 43 days ago

openmetadata-mcpai

OpenMetadata

Verified · 35 days ago

Official OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.

hand-reviewed15k starschecked 35 days ago