Skip to the card

2026-11-21 issue

Observed arrival · 2026-11-21

Toolmark records what AI-agent tools do in a sandbox

toolmark.dev Visit website
Editorial interest 84/100 Selection signal · not a rating of the site

It runs exact versions of MCP servers, skills, and plugins in an isolated sandbox, then compares observed behavior with the tools’ declared claims.

Landing page captured for the 2026-11-21 issue.
For
Teams reviewing MCP servers, agent skills, plugins, and API documents
Worth noticing
Outbound-capable tools are called last, only after network closure is verified, and with synthetic values.

Field notes

A package check starts by resolving the requested exact version, then runs in a fresh cloud sandbox with no network, no secrets, and a synthetic data folder. The sample contrasts declarations such as a “read-only” hint with observed changes, and marks uncalled tools as “not tested” rather than treating them as failures. The displayed example is described as a run against Toolmark’s own server with planted flaws.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use

One card from the complete issue

Straw-Goat Rehearsal

333,779 arrived 1,000 judged 980 catalogued Enter the complete issue
toolmark.dev

Landing page observed 2026-11-21. The live site may have changed.